@agentmemory/agentmemory 0.9.30 → 0.9.31
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/.env.example +39 -33
- package/AGENTS.md +8 -8
- package/README.md +173 -558
- package/dist/.env.example +39 -33
- package/dist/cli.d.mts.map +1 -1
- package/dist/cli.mjs +1741 -966
- package/dist/cli.mjs.map +1 -1
- package/dist/compression-recovery-CnhLQC6N.mjs +5912 -0
- package/dist/compression-recovery-CnhLQC6N.mjs.map +1 -0
- package/dist/{connect-B4_ca6BD.mjs → connect-BSLIAMpw.mjs} +874 -267
- package/dist/connect-BSLIAMpw.mjs.map +1 -0
- package/dist/hooks/_capture.d.mts +5 -2
- package/dist/hooks/_capture.d.mts.map +1 -1
- package/dist/hooks/_capture.mjs +55 -19
- package/dist/hooks/_capture.mjs.map +1 -1
- package/dist/hooks/notification.mjs +20 -6
- package/dist/hooks/notification.mjs.map +1 -1
- package/dist/hooks/post-commit.mjs +25 -5
- package/dist/hooks/post-commit.mjs.map +1 -1
- package/dist/hooks/post-tool-failure.mjs +12 -4
- package/dist/hooks/post-tool-failure.mjs.map +1 -1
- package/dist/hooks/post-tool-use.mjs +12 -4
- package/dist/hooks/post-tool-use.mjs.map +1 -1
- package/dist/hooks/pre-compact.mjs +37 -10
- package/dist/hooks/pre-compact.mjs.map +1 -1
- package/dist/hooks/pre-tool-use.mjs +25 -5
- package/dist/hooks/pre-tool-use.mjs.map +1 -1
- package/dist/hooks/prompt-submit.mjs +12 -4
- package/dist/hooks/prompt-submit.mjs.map +1 -1
- package/dist/hooks/session-end.mjs +47 -16
- package/dist/hooks/session-end.mjs.map +1 -1
- package/dist/hooks/session-start.mjs +37 -10
- package/dist/hooks/session-start.mjs.map +1 -1
- package/dist/hooks/stop.mjs +74 -72
- package/dist/hooks/stop.mjs.map +1 -1
- package/dist/hooks/subagent-start.mjs +13 -5
- package/dist/hooks/subagent-start.mjs.map +1 -1
- package/dist/hooks/subagent-stop.mjs +18 -6
- package/dist/hooks/subagent-stop.mjs.map +1 -1
- package/dist/hooks/task-completed.mjs +13 -5
- package/dist/hooks/task-completed.mjs.map +1 -1
- package/dist/{image-refs-T_urbwHM.mjs → image-refs-Cyta4Lf9.mjs} +2 -2
- package/dist/{image-refs-T_urbwHM.mjs.map → image-refs-Cyta4Lf9.mjs.map} +1 -1
- package/dist/index.mjs +8539 -4203
- package/dist/index.mjs.map +1 -1
- package/dist/integrations/dsh.d.mts +55 -0
- package/dist/integrations/dsh.d.mts.map +1 -0
- package/dist/integrations/dsh.mjs +1145 -0
- package/dist/integrations/dsh.mjs.map +1 -0
- package/dist/{keyed-mutex-DchXsyfP.mjs → keyed-mutex-DCUh7PG-.mjs} +58 -9
- package/dist/keyed-mutex-DCUh7PG-.mjs.map +1 -0
- package/dist/{secret-store-BnY3A50C.mjs → secret-store-D9GwO0xp.mjs} +535 -434
- package/dist/secret-store-D9GwO0xp.mjs.map +1 -0
- package/dist/session-arguments-zxsbbd8y.mjs +113 -0
- package/dist/session-arguments-zxsbbd8y.mjs.map +1 -0
- package/dist/{src-Jsq9LCeH.mjs → src-DaMtDzt_.mjs} +4087 -3788
- package/dist/src-DaMtDzt_.mjs.map +1 -0
- package/dist/{standalone-DKCdrf1d.mjs → standalone-BlqshyZ5.mjs} +213 -56
- package/dist/standalone-BlqshyZ5.mjs.map +1 -0
- package/dist/standalone.d.mts +1 -1
- package/dist/standalone.d.mts.map +1 -1
- package/dist/standalone.mjs +626 -73
- package/dist/standalone.mjs.map +1 -1
- package/dist/viewer/index.html +288 -140
- package/integrations/hermes/README.md +84 -0
- package/integrations/hermes/__init__.py +669 -0
- package/integrations/hermes/plugin.yaml +27 -0
- package/integrations/omp/LICENSE +190 -0
- package/integrations/omp/README.md +76 -0
- package/integrations/omp/capture.ts +1 -0
- package/integrations/omp/dist/index.mjs +1450 -0
- package/integrations/omp/index.ts +488 -0
- package/integrations/omp/package.json +13 -0
- package/integrations/omp/security.ts +67 -0
- package/integrations/omp/skills/agentmemory-agents/REFERENCE.md +32 -0
- package/integrations/omp/skills/agentmemory-agents/SKILL.md +48 -0
- package/integrations/omp/skills/agentmemory-agents/TROUBLESHOOTING.md +70 -0
- package/integrations/omp/skills/agentmemory-architecture/SKILL.md +33 -0
- package/integrations/omp/skills/agentmemory-architecture/TROUBLESHOOTING.md +70 -0
- package/integrations/omp/skills/agentmemory-config/REFERENCE.md +90 -0
- package/integrations/omp/skills/agentmemory-config/SKILL.md +78 -0
- package/integrations/omp/skills/agentmemory-config/TROUBLESHOOTING.md +70 -0
- package/integrations/omp/skills/agentmemory-hooks/REFERENCE.md +20 -0
- package/integrations/omp/skills/agentmemory-hooks/SKILL.md +49 -0
- package/integrations/omp/skills/agentmemory-hooks/TROUBLESHOOTING.md +70 -0
- package/integrations/omp/skills/agentmemory-mcp-tools/REFERENCE.md +66 -0
- package/integrations/omp/skills/agentmemory-mcp-tools/SKILL.md +42 -0
- package/integrations/omp/skills/agentmemory-mcp-tools/TROUBLESHOOTING.md +70 -0
- package/integrations/omp/skills/agentmemory-rest-api/REFERENCE.md +158 -0
- package/integrations/omp/skills/agentmemory-rest-api/SKILL.md +49 -0
- package/integrations/omp/skills/agentmemory-rest-api/TROUBLESHOOTING.md +70 -0
- package/integrations/omp/skills/commit-context/EXAMPLES.md +71 -0
- package/integrations/omp/skills/commit-context/SKILL.md +64 -0
- package/integrations/omp/skills/commit-context/TROUBLESHOOTING.md +70 -0
- package/integrations/omp/skills/commit-history/EXAMPLES.md +71 -0
- package/integrations/omp/skills/commit-history/SKILL.md +62 -0
- package/integrations/omp/skills/commit-history/TROUBLESHOOTING.md +70 -0
- package/integrations/omp/skills/forget/EXAMPLES.md +40 -0
- package/integrations/omp/skills/forget/SKILL.md +73 -0
- package/integrations/omp/skills/forget/TROUBLESHOOTING.md +70 -0
- package/integrations/omp/skills/handoff/EXAMPLES.md +57 -0
- package/integrations/omp/skills/handoff/SKILL.md +75 -0
- package/integrations/omp/skills/handoff/TROUBLESHOOTING.md +70 -0
- package/integrations/omp/skills/lesson/SKILL.md +64 -0
- package/integrations/omp/skills/lesson/TROUBLESHOOTING.md +70 -0
- package/integrations/omp/skills/memory-discipline/SKILL.md +65 -0
- package/integrations/omp/skills/memory-discipline/TROUBLESHOOTING.md +70 -0
- package/integrations/omp/skills/recall/EXAMPLES.md +74 -0
- package/integrations/omp/skills/recall/SKILL.md +74 -0
- package/integrations/omp/skills/recall/TROUBLESHOOTING.md +70 -0
- package/integrations/omp/skills/recap/EXAMPLES.md +62 -0
- package/integrations/omp/skills/recap/SKILL.md +68 -0
- package/integrations/omp/skills/recap/TROUBLESHOOTING.md +70 -0
- package/integrations/omp/skills/remember/EXAMPLES.md +67 -0
- package/integrations/omp/skills/remember/SKILL.md +66 -0
- package/integrations/omp/skills/remember/TROUBLESHOOTING.md +70 -0
- package/integrations/omp/skills/session-history/EXAMPLES.md +59 -0
- package/integrations/omp/skills/session-history/SKILL.md +67 -0
- package/integrations/omp/skills/session-history/TROUBLESHOOTING.md +70 -0
- package/integrations/omp/skills/write-agentmemory-skill/SKILL.md +41 -0
- package/integrations/omp/skills/write-agentmemory-skill/TROUBLESHOOTING.md +70 -0
- package/integrations/openclaw/LICENSE +190 -0
- package/integrations/openclaw/README.md +88 -0
- package/integrations/openclaw/openclaw.plugin.json +71 -0
- package/integrations/openclaw/package.json +38 -0
- package/integrations/openclaw/plugin.mjs +425 -0
- package/integrations/openclaw/plugin.yaml +26 -0
- package/integrations/openclaw/skills/agentmemory-agents/REFERENCE.md +32 -0
- package/integrations/openclaw/skills/agentmemory-agents/SKILL.md +48 -0
- package/integrations/openclaw/skills/agentmemory-agents/TROUBLESHOOTING.md +70 -0
- package/integrations/openclaw/skills/agentmemory-architecture/SKILL.md +33 -0
- package/integrations/openclaw/skills/agentmemory-architecture/TROUBLESHOOTING.md +70 -0
- package/integrations/openclaw/skills/agentmemory-config/REFERENCE.md +90 -0
- package/integrations/openclaw/skills/agentmemory-config/SKILL.md +78 -0
- package/integrations/openclaw/skills/agentmemory-config/TROUBLESHOOTING.md +70 -0
- package/integrations/openclaw/skills/agentmemory-hooks/REFERENCE.md +20 -0
- package/integrations/openclaw/skills/agentmemory-hooks/SKILL.md +49 -0
- package/integrations/openclaw/skills/agentmemory-hooks/TROUBLESHOOTING.md +70 -0
- package/integrations/openclaw/skills/agentmemory-mcp-tools/REFERENCE.md +66 -0
- package/integrations/openclaw/skills/agentmemory-mcp-tools/SKILL.md +42 -0
- package/integrations/openclaw/skills/agentmemory-mcp-tools/TROUBLESHOOTING.md +70 -0
- package/integrations/openclaw/skills/agentmemory-rest-api/REFERENCE.md +158 -0
- package/integrations/openclaw/skills/agentmemory-rest-api/SKILL.md +49 -0
- package/integrations/openclaw/skills/agentmemory-rest-api/TROUBLESHOOTING.md +70 -0
- package/integrations/openclaw/skills/commit-context/EXAMPLES.md +71 -0
- package/integrations/openclaw/skills/commit-context/SKILL.md +64 -0
- package/integrations/openclaw/skills/commit-context/TROUBLESHOOTING.md +70 -0
- package/integrations/openclaw/skills/commit-history/EXAMPLES.md +71 -0
- package/integrations/openclaw/skills/commit-history/SKILL.md +62 -0
- package/integrations/openclaw/skills/commit-history/TROUBLESHOOTING.md +70 -0
- package/integrations/openclaw/skills/forget/EXAMPLES.md +40 -0
- package/integrations/openclaw/skills/forget/SKILL.md +73 -0
- package/integrations/openclaw/skills/forget/TROUBLESHOOTING.md +70 -0
- package/integrations/openclaw/skills/handoff/EXAMPLES.md +57 -0
- package/integrations/openclaw/skills/handoff/SKILL.md +75 -0
- package/integrations/openclaw/skills/handoff/TROUBLESHOOTING.md +70 -0
- package/integrations/openclaw/skills/lesson/SKILL.md +64 -0
- package/integrations/openclaw/skills/lesson/TROUBLESHOOTING.md +70 -0
- package/integrations/openclaw/skills/memory-discipline/SKILL.md +65 -0
- package/integrations/openclaw/skills/memory-discipline/TROUBLESHOOTING.md +70 -0
- package/integrations/openclaw/skills/recall/EXAMPLES.md +74 -0
- package/integrations/openclaw/skills/recall/SKILL.md +74 -0
- package/integrations/openclaw/skills/recall/TROUBLESHOOTING.md +70 -0
- package/integrations/openclaw/skills/recap/EXAMPLES.md +62 -0
- package/integrations/openclaw/skills/recap/SKILL.md +68 -0
- package/integrations/openclaw/skills/recap/TROUBLESHOOTING.md +70 -0
- package/integrations/openclaw/skills/remember/EXAMPLES.md +67 -0
- package/integrations/openclaw/skills/remember/SKILL.md +66 -0
- package/integrations/openclaw/skills/remember/TROUBLESHOOTING.md +70 -0
- package/integrations/openclaw/skills/session-history/EXAMPLES.md +59 -0
- package/integrations/openclaw/skills/session-history/SKILL.md +67 -0
- package/integrations/openclaw/skills/session-history/TROUBLESHOOTING.md +70 -0
- package/integrations/openclaw/skills/write-agentmemory-skill/SKILL.md +41 -0
- package/integrations/openclaw/skills/write-agentmemory-skill/TROUBLESHOOTING.md +70 -0
- package/integrations/pi/LICENSE +190 -0
- package/integrations/pi/README.md +45 -51
- package/integrations/pi/dist/index.mjs +1379 -0
- package/integrations/pi/index.ts +138 -171
- package/integrations/pi/package.json +16 -6
- package/integrations/pi/security.ts +6 -26
- package/integrations/pi/skills/agentmemory-agents/REFERENCE.md +32 -0
- package/integrations/pi/skills/agentmemory-agents/SKILL.md +48 -0
- package/integrations/pi/skills/agentmemory-agents/TROUBLESHOOTING.md +70 -0
- package/integrations/pi/skills/agentmemory-architecture/SKILL.md +33 -0
- package/integrations/pi/skills/agentmemory-architecture/TROUBLESHOOTING.md +70 -0
- package/integrations/pi/skills/agentmemory-config/REFERENCE.md +90 -0
- package/integrations/pi/skills/agentmemory-config/SKILL.md +78 -0
- package/integrations/pi/skills/agentmemory-config/TROUBLESHOOTING.md +70 -0
- package/integrations/pi/skills/agentmemory-hooks/REFERENCE.md +20 -0
- package/integrations/pi/skills/agentmemory-hooks/SKILL.md +49 -0
- package/integrations/pi/skills/agentmemory-hooks/TROUBLESHOOTING.md +70 -0
- package/integrations/pi/skills/agentmemory-mcp-tools/REFERENCE.md +66 -0
- package/integrations/pi/skills/agentmemory-mcp-tools/SKILL.md +42 -0
- package/integrations/pi/skills/agentmemory-mcp-tools/TROUBLESHOOTING.md +70 -0
- package/integrations/pi/skills/agentmemory-rest-api/REFERENCE.md +158 -0
- package/integrations/pi/skills/agentmemory-rest-api/SKILL.md +49 -0
- package/integrations/pi/skills/agentmemory-rest-api/TROUBLESHOOTING.md +70 -0
- package/integrations/pi/skills/commit-context/EXAMPLES.md +71 -0
- package/integrations/pi/skills/commit-context/SKILL.md +64 -0
- package/integrations/pi/skills/commit-context/TROUBLESHOOTING.md +70 -0
- package/integrations/pi/skills/commit-history/EXAMPLES.md +71 -0
- package/integrations/pi/skills/commit-history/SKILL.md +62 -0
- package/integrations/pi/skills/commit-history/TROUBLESHOOTING.md +70 -0
- package/integrations/pi/skills/forget/EXAMPLES.md +40 -0
- package/integrations/pi/skills/forget/SKILL.md +73 -0
- package/integrations/pi/skills/forget/TROUBLESHOOTING.md +70 -0
- package/integrations/pi/skills/handoff/EXAMPLES.md +57 -0
- package/integrations/pi/skills/handoff/SKILL.md +75 -0
- package/integrations/pi/skills/handoff/TROUBLESHOOTING.md +70 -0
- package/integrations/pi/skills/lesson/SKILL.md +64 -0
- package/integrations/pi/skills/lesson/TROUBLESHOOTING.md +70 -0
- package/integrations/pi/skills/memory-discipline/SKILL.md +65 -0
- package/integrations/pi/skills/memory-discipline/TROUBLESHOOTING.md +70 -0
- package/integrations/pi/skills/recall/EXAMPLES.md +74 -0
- package/integrations/pi/skills/recall/SKILL.md +74 -0
- package/integrations/pi/skills/recall/TROUBLESHOOTING.md +70 -0
- package/integrations/pi/skills/recap/EXAMPLES.md +62 -0
- package/integrations/pi/skills/recap/SKILL.md +68 -0
- package/integrations/pi/skills/recap/TROUBLESHOOTING.md +70 -0
- package/integrations/pi/skills/remember/EXAMPLES.md +67 -0
- package/integrations/pi/skills/remember/SKILL.md +66 -0
- package/integrations/pi/skills/remember/TROUBLESHOOTING.md +70 -0
- package/integrations/pi/skills/session-history/EXAMPLES.md +59 -0
- package/integrations/pi/skills/session-history/SKILL.md +67 -0
- package/integrations/pi/skills/session-history/TROUBLESHOOTING.md +70 -0
- package/integrations/pi/skills/write-agentmemory-skill/SKILL.md +41 -0
- package/integrations/pi/skills/write-agentmemory-skill/TROUBLESHOOTING.md +70 -0
- package/package.json +32 -11
- package/plugin/.claude-plugin/plugin.json +1 -1
- package/plugin/.codex-plugin/plugin.json +4 -3
- package/plugin/.devin-plugin/plugin.json +5 -3
- package/plugin/cursor/hooks.json +23 -8
- package/plugin/hooks.json +67 -0
- package/plugin/opencode/README.md +1 -1
- package/plugin/opencode/agentmemory-capture.ts +25 -11
- package/plugin/opencode/plugin.json +1 -1
- package/plugin/plugin.json +1 -1
- package/plugin/scripts/_capture.d.mts +5 -2
- package/plugin/scripts/_capture.d.mts.map +1 -1
- package/plugin/scripts/_capture.mjs +55 -19
- package/plugin/scripts/_capture.mjs.map +1 -1
- package/plugin/scripts/cursor/run-detached.d.mts +1 -0
- package/plugin/scripts/cursor/run-detached.mjs +786 -0
- package/plugin/scripts/cursor/run-detached.mjs.map +1 -0
- package/plugin/scripts/cursor/run-hook.d.mts +1 -0
- package/plugin/scripts/cursor/run-hook.mjs +704 -0
- package/plugin/scripts/cursor/run-hook.mjs.map +1 -0
- package/plugin/scripts/notification.mjs +20 -6
- package/plugin/scripts/notification.mjs.map +1 -1
- package/plugin/scripts/plugin-bridge.mjs +37 -6
- package/plugin/scripts/post-commit.mjs +25 -5
- package/plugin/scripts/post-commit.mjs.map +1 -1
- package/plugin/scripts/post-tool-failure.mjs +12 -4
- package/plugin/scripts/post-tool-failure.mjs.map +1 -1
- package/plugin/scripts/post-tool-use.mjs +12 -4
- package/plugin/scripts/post-tool-use.mjs.map +1 -1
- package/plugin/scripts/pre-compact.mjs +37 -10
- package/plugin/scripts/pre-compact.mjs.map +1 -1
- package/plugin/scripts/pre-tool-use.mjs +25 -5
- package/plugin/scripts/pre-tool-use.mjs.map +1 -1
- package/plugin/scripts/prompt-submit.mjs +12 -4
- package/plugin/scripts/prompt-submit.mjs.map +1 -1
- package/plugin/scripts/session-end.mjs +47 -16
- package/plugin/scripts/session-end.mjs.map +1 -1
- package/plugin/scripts/session-start.mjs +37 -10
- package/plugin/scripts/session-start.mjs.map +1 -1
- package/plugin/scripts/stop.mjs +74 -72
- package/plugin/scripts/stop.mjs.map +1 -1
- package/plugin/scripts/subagent-start.mjs +13 -5
- package/plugin/scripts/subagent-start.mjs.map +1 -1
- package/plugin/scripts/subagent-stop.mjs +18 -6
- package/plugin/scripts/subagent-stop.mjs.map +1 -1
- package/plugin/scripts/task-completed.mjs +13 -5
- package/plugin/scripts/task-completed.mjs.map +1 -1
- package/plugin/skills/_shared/TROUBLESHOOTING.md +21 -7
- package/plugin/skills/agentmemory-agents/REFERENCE.md +7 -6
- package/plugin/skills/agentmemory-agents/SKILL.md +19 -5
- package/plugin/skills/agentmemory-agents/TROUBLESHOOTING.md +70 -0
- package/plugin/skills/agentmemory-architecture/SKILL.md +4 -4
- package/plugin/skills/agentmemory-architecture/TROUBLESHOOTING.md +70 -0
- package/plugin/skills/agentmemory-config/REFERENCE.md +12 -15
- package/plugin/skills/agentmemory-config/SKILL.md +7 -3
- package/plugin/skills/agentmemory-config/TROUBLESHOOTING.md +70 -0
- package/plugin/skills/agentmemory-hooks/SKILL.md +15 -5
- package/plugin/skills/agentmemory-hooks/TROUBLESHOOTING.md +70 -0
- package/plugin/skills/agentmemory-mcp-tools/REFERENCE.md +4 -4
- package/plugin/skills/agentmemory-mcp-tools/SKILL.md +6 -3
- package/plugin/skills/agentmemory-mcp-tools/TROUBLESHOOTING.md +70 -0
- package/plugin/skills/agentmemory-rest-api/REFERENCE.md +9 -1
- package/plugin/skills/agentmemory-rest-api/SKILL.md +12 -6
- package/plugin/skills/agentmemory-rest-api/TROUBLESHOOTING.md +70 -0
- package/plugin/skills/commit-context/SKILL.md +1 -1
- package/plugin/skills/commit-context/TROUBLESHOOTING.md +70 -0
- package/plugin/skills/commit-history/SKILL.md +1 -1
- package/plugin/skills/commit-history/TROUBLESHOOTING.md +70 -0
- package/plugin/skills/forget/EXAMPLES.md +19 -54
- package/plugin/skills/forget/SKILL.md +16 -12
- package/plugin/skills/forget/TROUBLESHOOTING.md +70 -0
- package/plugin/skills/handoff/EXAMPLES.md +5 -4
- package/plugin/skills/handoff/SKILL.md +10 -5
- package/plugin/skills/handoff/TROUBLESHOOTING.md +70 -0
- package/plugin/skills/lesson/SKILL.md +1 -1
- package/plugin/skills/lesson/TROUBLESHOOTING.md +70 -0
- package/plugin/skills/memory-discipline/SKILL.md +1 -1
- package/plugin/skills/memory-discipline/TROUBLESHOOTING.md +70 -0
- package/plugin/skills/recall/SKILL.md +18 -7
- package/plugin/skills/recall/TROUBLESHOOTING.md +70 -0
- package/plugin/skills/recap/EXAMPLES.md +5 -3
- package/plugin/skills/recap/SKILL.md +11 -6
- package/plugin/skills/recap/TROUBLESHOOTING.md +70 -0
- package/plugin/skills/remember/EXAMPLES.md +3 -3
- package/plugin/skills/remember/SKILL.md +1 -1
- package/plugin/skills/remember/TROUBLESHOOTING.md +70 -0
- package/plugin/skills/session-history/EXAMPLES.md +2 -2
- package/plugin/skills/session-history/SKILL.md +10 -4
- package/plugin/skills/session-history/TROUBLESHOOTING.md +70 -0
- package/plugin/skills/write-agentmemory-skill/SKILL.md +2 -1
- package/plugin/skills/write-agentmemory-skill/TROUBLESHOOTING.md +70 -0
- package/dist/connect-B4_ca6BD.mjs.map +0 -1
- package/dist/docker-compose.yml +0 -73
- package/dist/iii-config.docker.yaml +0 -53
- package/dist/iii-config.yaml +0 -63
- package/dist/keyed-mutex-DchXsyfP.mjs.map +0 -1
- package/dist/secret-store-BnY3A50C.mjs.map +0 -1
- package/dist/src-Jsq9LCeH.mjs.map +0 -1
- package/dist/standalone-DKCdrf1d.mjs.map +0 -1
- package/dist/status-IRz7ta8-.mjs +0 -2344
- package/dist/status-IRz7ta8-.mjs.map +0 -1
- package/docker-compose.yml +0 -73
- package/iii-config.docker.yaml +0 -53
- package/iii-config.yaml +0 -63
|
@@ -0,0 +1,66 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: remember
|
|
3
|
+
description: Save an insight, decision, or learning to agentmemory's long-term storage with searchable concept tags. Use when the user says "remember this", "save this", "note that", "don't forget", or wants to preserve knowledge for future sessions.
|
|
4
|
+
argument-hint: "[what to remember]"
|
|
5
|
+
user-invocable: true
|
|
6
|
+
---
|
|
7
|
+
|
|
8
|
+
The user wants to save this to long-term memory: $ARGUMENTS
|
|
9
|
+
|
|
10
|
+
## Quick start
|
|
11
|
+
|
|
12
|
+
```json
|
|
13
|
+
memory_save {
|
|
14
|
+
"content": "We rotate JWT refresh tokens on every use; the old token is revoked server-side in auth/refresh.ts.",
|
|
15
|
+
"concepts": "jwt-refresh-rotation, token-revocation, auth-flow",
|
|
16
|
+
"files": "src/auth/refresh.ts"
|
|
17
|
+
}
|
|
18
|
+
```
|
|
19
|
+
|
|
20
|
+
Expected output:
|
|
21
|
+
|
|
22
|
+
```text
|
|
23
|
+
Saved memory abc12345 with 3 concepts: jwt-refresh-rotation, token-revocation, auth-flow.
|
|
24
|
+
```
|
|
25
|
+
|
|
26
|
+
## Why
|
|
27
|
+
|
|
28
|
+
A memory is only as useful as the terms that retrieve it. Tag with specific
|
|
29
|
+
concepts so a future `recall` finds it, and preserve the user's own phrasing.
|
|
30
|
+
|
|
31
|
+
## Workflow
|
|
32
|
+
|
|
33
|
+
1. Pull the core insight, decision, or fact out of `$ARGUMENTS`.
|
|
34
|
+
2. Extract 2-5 lowercased concept phrases. Prefer specific over generic
|
|
35
|
+
(`jwt-refresh-rotation` beats `auth`).
|
|
36
|
+
3. Extract referenced file paths (absolute or repo-relative). Empty if none.
|
|
37
|
+
4. Call `memory_save` with `content`, `concepts` (comma-separated string), and
|
|
38
|
+
`files` (comma-separated string). In a multi-agent setup pass `agentId` so
|
|
39
|
+
the memory lands in the right agent's scope.
|
|
40
|
+
5. Confirm the save and echo the concepts so the user knows the retrieval terms.
|
|
41
|
+
6. To update a fact, save the corrected version outright: near-duplicate content
|
|
42
|
+
supersedes the old record, which leaves recall but stays in the version chain.
|
|
43
|
+
|
|
44
|
+
## Anti-patterns
|
|
45
|
+
|
|
46
|
+
WRONG: `concepts: "stuff, code, notes"` (generic tags nothing can find later).
|
|
47
|
+
|
|
48
|
+
RIGHT: `concepts: "jwt-refresh-rotation, token-revocation"` (specific, retrievable).
|
|
49
|
+
|
|
50
|
+
## Checklist
|
|
51
|
+
|
|
52
|
+
- Content preserves the user's phrasing, not a paraphrase.
|
|
53
|
+
- Concepts are specific, lowercased, 2-5 items.
|
|
54
|
+
- File paths are real references, not guesses.
|
|
55
|
+
- Confirmation echoes the exact concepts tagged.
|
|
56
|
+
|
|
57
|
+
## See also
|
|
58
|
+
|
|
59
|
+
- `recall`: retrieve what you save here (the pair to this skill).
|
|
60
|
+
- `forget`: remove a memory you saved by mistake.
|
|
61
|
+
- `lesson`: behavioral rules from corrections; memories are for facts.
|
|
62
|
+
- `memory-discipline`: when to save unprompted.
|
|
63
|
+
|
|
64
|
+
## Troubleshooting
|
|
65
|
+
|
|
66
|
+
See [TROUBLESHOOTING.md](TROUBLESHOOTING.md) if `memory_save` is not available.
|
|
@@ -0,0 +1,70 @@
|
|
|
1
|
+
<!-- AUTOGEN:troubleshooting START - generated by scripts/skills/generate.ts, do not edit by hand -->
|
|
2
|
+
# Troubleshooting agentmemory skills
|
|
3
|
+
|
|
4
|
+
Recovery steps for separately installed skills. This document is generated into
|
|
5
|
+
each skill directory so native skill readers can open it without parent traversal.
|
|
6
|
+
|
|
7
|
+
## "MCP tool not available"
|
|
8
|
+
|
|
9
|
+
Missing tools can mean a stopped MCP process, a disconnected daemon, or an
|
|
10
|
+
explicitly reduced tool surface. Walk these in order:
|
|
11
|
+
|
|
12
|
+
1. Identify the host. In Claude Code, inspect `/plugin list` and `/mcp`.
|
|
13
|
+
In Hermes, inspect the configured memory provider and `mcp_servers` separately.
|
|
14
|
+
In OpenClaw, validate the host configuration and inspect its MCP servers and
|
|
15
|
+
native plugins separately. In Pi or OMP, inspect `/agentmemory-status` and the
|
|
16
|
+
MCP inventory separately; native save/search does not prove the broader tools
|
|
17
|
+
are connected. Do not run another host's setup commands.
|
|
18
|
+
2. Restart or reload the affected host connection after configuration changes.
|
|
19
|
+
3. Inspect the connected tool inventory. Hermes may namespace MCP tools; invoke
|
|
20
|
+
the actual advertised names and schemas. A native memory provider is not
|
|
21
|
+
proof that every MCP tool or shared skill is available.
|
|
22
|
+
4. Check `agentmemory status` and the daemon's `AGENTMEMORY_TOOLS` setting.
|
|
23
|
+
Codex's bundled bridge lists the daemon's enabled tools. The standalone shim
|
|
24
|
+
used by other hosts can fall back to seven basic tools with a separate store.
|
|
25
|
+
Do not claim full daemon functionality based on those seven tools.
|
|
26
|
+
5. If `agentmemory connect codex` and the Codex plugin are both enabled, choose
|
|
27
|
+
one MCP connection. Check `/hooks` before adding global hook fallbacks.
|
|
28
|
+
|
|
29
|
+
Hermes, OpenClaw, Pi and OMP connector installations bundle skills; other hosts
|
|
30
|
+
may install them separately. Check the host's skill inventory and open this file
|
|
31
|
+
from the installed skill directory. Test automatic capture with a real turn and
|
|
32
|
+
a recorded observation; tool connectivity alone does not establish lifecycle
|
|
33
|
+
capture.
|
|
34
|
+
|
|
35
|
+
An outage or timeout is not an empty search result. Report the failure. A write
|
|
36
|
+
may have committed before the response was lost; inspect state before retrying.
|
|
37
|
+
|
|
38
|
+
## REST fallback
|
|
39
|
+
|
|
40
|
+
When the MCP tools stay unavailable but the daemon is running, call the REST
|
|
41
|
+
API directly:
|
|
42
|
+
|
|
43
|
+
1. Set `AGENTMEMORY_URL` to the daemon base URL (default `http://localhost:3111`).
|
|
44
|
+
2. The REST API requires a bearer credential by default. Use the host's explicit
|
|
45
|
+
`AGENTMEMORY_SECRET`; for loopback URLs only, fall back to the secret in
|
|
46
|
+
`~/.agentmemory/.env` and then `~/.agentmemory/secret`. Load the value locally
|
|
47
|
+
without displaying it. Never send a local-file secret to a remote URL.
|
|
48
|
+
If `AGENTMEMORY_CREDENTIAL_MODE=explicit`, require the explicit host credential
|
|
49
|
+
and do not read local credential files.
|
|
50
|
+
Authenticated REST fallback requests require HTTPS for non-loopback
|
|
51
|
+
URLs; HTTP is allowed for loopback URLs (`localhost`, `127.0.0.0/8`, or `[::1]`).
|
|
52
|
+
Reject redirects on authenticated requests. Do not print or save the secret.
|
|
53
|
+
|
|
54
|
+
Endpoint map by skill:
|
|
55
|
+
|
|
56
|
+
| Skill | REST call |
|
|
57
|
+
| --------------- | --------------------------------------------------------------- |
|
|
58
|
+
| remember | `POST /agentmemory/remember` |
|
|
59
|
+
| recall | `POST /agentmemory/smart-search` |
|
|
60
|
+
| recap | `GET /agentmemory/sessions` + `POST /agentmemory/smart-search` |
|
|
61
|
+
| handoff | `GET /agentmemory/sessions` + `POST /agentmemory/smart-search` |
|
|
62
|
+
| session-history | `GET /agentmemory/sessions` |
|
|
63
|
+
| commit-context | `GET /agentmemory/session/by-commit?sha=<sha>` |
|
|
64
|
+
| commit-history | `GET /agentmemory/commits` (URL-encode every query param) |
|
|
65
|
+
|
|
66
|
+
The MCP host reads the plugin MCP configuration. Restart the daemon after
|
|
67
|
+
changing its configuration, then restart or reconnect the host MCP process after
|
|
68
|
+
changing its URL or explicit secret. The local bridge reads the credential files
|
|
69
|
+
for each request; it does not inherit other daemon `.env` settings.
|
|
70
|
+
<!-- AUTOGEN:troubleshooting END -->
|
|
@@ -0,0 +1,59 @@
|
|
|
1
|
+
# session-history worked examples
|
|
2
|
+
|
|
3
|
+
## 1. Standard timeline
|
|
4
|
+
|
|
5
|
+
User: "Show me the session history."
|
|
6
|
+
|
|
7
|
+
Invocation:
|
|
8
|
+
|
|
9
|
+
```json
|
|
10
|
+
memory_sessions { "project": "app", "limit": 20 }
|
|
11
|
+
```
|
|
12
|
+
|
|
13
|
+
Response:
|
|
14
|
+
|
|
15
|
+
```json
|
|
16
|
+
{
|
|
17
|
+
"sessions": [
|
|
18
|
+
{ "id": "7f3a9c21", "project": "app", "startedAt": "2026-06-07T09:00:00Z",
|
|
19
|
+
"status": "completed", "observationCount": 14,
|
|
20
|
+
"summary": "Reworked refresh rotation",
|
|
21
|
+
"highlights": [ { "type": "decision", "title": "Rotate refresh tokens on every use" } ] },
|
|
22
|
+
{ "id": "b21d004e", "project": "app", "startedAt": "2026-06-05T14:00:00Z",
|
|
23
|
+
"status": "completed", "observationCount": 9,
|
|
24
|
+
"highlights": [ { "type": "code", "title": "limit.ts counts per-IP" } ] }
|
|
25
|
+
]
|
|
26
|
+
}
|
|
27
|
+
```
|
|
28
|
+
|
|
29
|
+
Present:
|
|
30
|
+
|
|
31
|
+
> - `7f3a9c2` app, 2026-06-07 09:00, completed, 14 obs
|
|
32
|
+
> - decision: Rotate refresh tokens on every use (summary: Reworked refresh rotation)
|
|
33
|
+
> - `b21d004` app, 2026-06-05 14:00, completed, 9 obs
|
|
34
|
+
> - code: limit.ts counts per-IP
|
|
35
|
+
|
|
36
|
+
## 2. Session with no observations
|
|
37
|
+
|
|
38
|
+
If a returned session has `observationCount: 0`, list it but say so:
|
|
39
|
+
|
|
40
|
+
> - `c98f110` app, 2026-06-04 11:00, abandoned, 0 obs (no recorded work)
|
|
41
|
+
|
|
42
|
+
## 3. Empty history
|
|
43
|
+
|
|
44
|
+
User: "What did we do last time?"
|
|
45
|
+
|
|
46
|
+
```json
|
|
47
|
+
memory_sessions { "project": "app", "limit": 20 }
|
|
48
|
+
```
|
|
49
|
+
|
|
50
|
+
Response:
|
|
51
|
+
|
|
52
|
+
```json
|
|
53
|
+
{ "sessions": [] }
|
|
54
|
+
```
|
|
55
|
+
|
|
56
|
+
Present:
|
|
57
|
+
|
|
58
|
+
> No recorded sessions yet for this project. Once you work with memory capture
|
|
59
|
+
> on, they will show here. Use `remember` to save a note now.
|
|
@@ -0,0 +1,67 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: session-history
|
|
3
|
+
description: Show what happened in recent past sessions on this project as a clean timeline. Use when the user asks "what did we do last time", "session history", "past sessions", or wants an overview of previous work.
|
|
4
|
+
user-invocable: true
|
|
5
|
+
---
|
|
6
|
+
|
|
7
|
+
The user wants an overview of recent sessions on this project.
|
|
8
|
+
|
|
9
|
+
## Quick start
|
|
10
|
+
|
|
11
|
+
```json
|
|
12
|
+
memory_sessions { "project": "<current-project-id>", "limit": 20 }
|
|
13
|
+
```
|
|
14
|
+
|
|
15
|
+
Expected output:
|
|
16
|
+
|
|
17
|
+
```text
|
|
18
|
+
7f3a9c2 · app · 2026-06-07 09:00 · completed · 14 obs
|
|
19
|
+
- decision: Rotate refresh tokens on every use
|
|
20
|
+
b21d004 · app · 2026-06-05 14:00 · completed · 9 obs
|
|
21
|
+
- code: limit.ts counts per-IP
|
|
22
|
+
```
|
|
23
|
+
|
|
24
|
+
## Why
|
|
25
|
+
|
|
26
|
+
Only show sessions and observations the tool returned. An empty history is a
|
|
27
|
+
real answer, never a cue to invent past work.
|
|
28
|
+
|
|
29
|
+
## Workflow
|
|
30
|
+
|
|
31
|
+
1. Use the exact project identifier recorded by the host and pass it to
|
|
32
|
+
`memory_sessions`, with `agentId` when requested. If it is unknown, page
|
|
33
|
+
through sessions using `nextCursor` and match normalized `cwd` by directory
|
|
34
|
+
boundary before choosing the most recent 20. Never substitute another project.
|
|
35
|
+
2. Preserve scope filters on every page; stop at the requested count or a null
|
|
36
|
+
`nextCursor`. State when the displayed history is a partial page. Present in
|
|
37
|
+
reverse chronological order: session id (first 8), project, start
|
|
38
|
+
time, status.
|
|
39
|
+
3. For sessions with observations, show the key highlights (type plus title).
|
|
40
|
+
4. Note the total observation count per session.
|
|
41
|
+
5. When a session summary exists, surface its title and the key decisions.
|
|
42
|
+
|
|
43
|
+
## Anti-patterns
|
|
44
|
+
|
|
45
|
+
WRONG: the tool returns two sessions, you describe "several sessions of steady
|
|
46
|
+
progress" and add ones you remember from the conversation.
|
|
47
|
+
|
|
48
|
+
RIGHT: show exactly the two sessions returned, each with its real id, status, and
|
|
49
|
+
observation count.
|
|
50
|
+
|
|
51
|
+
## Checklist
|
|
52
|
+
|
|
53
|
+
- Every session shown came from the tool response.
|
|
54
|
+
- Project/directory scope was checked before selecting the displayed window.
|
|
55
|
+
- Order is reverse-chronological.
|
|
56
|
+
- Per-session observation counts match the response.
|
|
57
|
+
- No session or highlight was invented or merged.
|
|
58
|
+
|
|
59
|
+
## See also
|
|
60
|
+
|
|
61
|
+
- `recap`: same data grouped by date with highlights.
|
|
62
|
+
- `handoff`: jump straight into the most recent session.
|
|
63
|
+
- `recall`: search across all sessions by topic.
|
|
64
|
+
|
|
65
|
+
## Troubleshooting
|
|
66
|
+
|
|
67
|
+
See [TROUBLESHOOTING.md](TROUBLESHOOTING.md) if `memory_sessions` is not available.
|
|
@@ -0,0 +1,70 @@
|
|
|
1
|
+
<!-- AUTOGEN:troubleshooting START - generated by scripts/skills/generate.ts, do not edit by hand -->
|
|
2
|
+
# Troubleshooting agentmemory skills
|
|
3
|
+
|
|
4
|
+
Recovery steps for separately installed skills. This document is generated into
|
|
5
|
+
each skill directory so native skill readers can open it without parent traversal.
|
|
6
|
+
|
|
7
|
+
## "MCP tool not available"
|
|
8
|
+
|
|
9
|
+
Missing tools can mean a stopped MCP process, a disconnected daemon, or an
|
|
10
|
+
explicitly reduced tool surface. Walk these in order:
|
|
11
|
+
|
|
12
|
+
1. Identify the host. In Claude Code, inspect `/plugin list` and `/mcp`.
|
|
13
|
+
In Hermes, inspect the configured memory provider and `mcp_servers` separately.
|
|
14
|
+
In OpenClaw, validate the host configuration and inspect its MCP servers and
|
|
15
|
+
native plugins separately. In Pi or OMP, inspect `/agentmemory-status` and the
|
|
16
|
+
MCP inventory separately; native save/search does not prove the broader tools
|
|
17
|
+
are connected. Do not run another host's setup commands.
|
|
18
|
+
2. Restart or reload the affected host connection after configuration changes.
|
|
19
|
+
3. Inspect the connected tool inventory. Hermes may namespace MCP tools; invoke
|
|
20
|
+
the actual advertised names and schemas. A native memory provider is not
|
|
21
|
+
proof that every MCP tool or shared skill is available.
|
|
22
|
+
4. Check `agentmemory status` and the daemon's `AGENTMEMORY_TOOLS` setting.
|
|
23
|
+
Codex's bundled bridge lists the daemon's enabled tools. The standalone shim
|
|
24
|
+
used by other hosts can fall back to seven basic tools with a separate store.
|
|
25
|
+
Do not claim full daemon functionality based on those seven tools.
|
|
26
|
+
5. If `agentmemory connect codex` and the Codex plugin are both enabled, choose
|
|
27
|
+
one MCP connection. Check `/hooks` before adding global hook fallbacks.
|
|
28
|
+
|
|
29
|
+
Hermes, OpenClaw, Pi and OMP connector installations bundle skills; other hosts
|
|
30
|
+
may install them separately. Check the host's skill inventory and open this file
|
|
31
|
+
from the installed skill directory. Test automatic capture with a real turn and
|
|
32
|
+
a recorded observation; tool connectivity alone does not establish lifecycle
|
|
33
|
+
capture.
|
|
34
|
+
|
|
35
|
+
An outage or timeout is not an empty search result. Report the failure. A write
|
|
36
|
+
may have committed before the response was lost; inspect state before retrying.
|
|
37
|
+
|
|
38
|
+
## REST fallback
|
|
39
|
+
|
|
40
|
+
When the MCP tools stay unavailable but the daemon is running, call the REST
|
|
41
|
+
API directly:
|
|
42
|
+
|
|
43
|
+
1. Set `AGENTMEMORY_URL` to the daemon base URL (default `http://localhost:3111`).
|
|
44
|
+
2. The REST API requires a bearer credential by default. Use the host's explicit
|
|
45
|
+
`AGENTMEMORY_SECRET`; for loopback URLs only, fall back to the secret in
|
|
46
|
+
`~/.agentmemory/.env` and then `~/.agentmemory/secret`. Load the value locally
|
|
47
|
+
without displaying it. Never send a local-file secret to a remote URL.
|
|
48
|
+
If `AGENTMEMORY_CREDENTIAL_MODE=explicit`, require the explicit host credential
|
|
49
|
+
and do not read local credential files.
|
|
50
|
+
Authenticated REST fallback requests require HTTPS for non-loopback
|
|
51
|
+
URLs; HTTP is allowed for loopback URLs (`localhost`, `127.0.0.0/8`, or `[::1]`).
|
|
52
|
+
Reject redirects on authenticated requests. Do not print or save the secret.
|
|
53
|
+
|
|
54
|
+
Endpoint map by skill:
|
|
55
|
+
|
|
56
|
+
| Skill | REST call |
|
|
57
|
+
| --------------- | --------------------------------------------------------------- |
|
|
58
|
+
| remember | `POST /agentmemory/remember` |
|
|
59
|
+
| recall | `POST /agentmemory/smart-search` |
|
|
60
|
+
| recap | `GET /agentmemory/sessions` + `POST /agentmemory/smart-search` |
|
|
61
|
+
| handoff | `GET /agentmemory/sessions` + `POST /agentmemory/smart-search` |
|
|
62
|
+
| session-history | `GET /agentmemory/sessions` |
|
|
63
|
+
| commit-context | `GET /agentmemory/session/by-commit?sha=<sha>` |
|
|
64
|
+
| commit-history | `GET /agentmemory/commits` (URL-encode every query param) |
|
|
65
|
+
|
|
66
|
+
The MCP host reads the plugin MCP configuration. Restart the daemon after
|
|
67
|
+
changing its configuration, then restart or reconnect the host MCP process after
|
|
68
|
+
changing its URL or explicit secret. The local bridge reads the credential files
|
|
69
|
+
for each request; it does not inherit other daemon `.env` settings.
|
|
70
|
+
<!-- AUTOGEN:troubleshooting END -->
|
|
@@ -0,0 +1,41 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: write-agentmemory-skill
|
|
3
|
+
description: The house format and rules for writing or updating an agentmemory skill. Use when adding a new skill, restructuring an existing one, or reviewing a skill contribution for consistency.
|
|
4
|
+
user-invocable: false
|
|
5
|
+
---
|
|
6
|
+
|
|
7
|
+
agentmemory skills follow one tiered format so they stay skimmable, accurate, and current. Match it exactly.
|
|
8
|
+
|
|
9
|
+
## Directory layout
|
|
10
|
+
|
|
11
|
+
```text
|
|
12
|
+
plugin/skills/<name>/
|
|
13
|
+
SKILL.md (required, under 100 lines)
|
|
14
|
+
REFERENCE.md (optional, dense facts; auto-generate data tables)
|
|
15
|
+
EXAMPLES.md (optional, worked transcripts)
|
|
16
|
+
TROUBLESHOOTING.md (generated support file)
|
|
17
|
+
```
|
|
18
|
+
|
|
19
|
+
## SKILL.md rules
|
|
20
|
+
|
|
21
|
+
- Frontmatter: `name`, `description`, optional `argument-hint`, and `user-invocable`. Set `user-invocable: true` only for skills the user runs as a slash command; reference and knowledge skills are `false`.
|
|
22
|
+
- Description is two sentences and the only thing the agent sees when deciding to load the skill. Sentence one states the capability. Sentence two starts "Use when" and lists concrete triggers. Keep it distinct from sibling skills, under 1024 chars, third person.
|
|
23
|
+
- Body order: Quick start (one concrete example), Why (the governing principle), Workflow (numbered steps with decision gates), Anti-patterns (a WRONG vs RIGHT callout for the top mistake), Checklist, See also (cross-link siblings), Reference or Troubleshooting pointer.
|
|
24
|
+
- Stay under 100 lines. Move dense facts to REFERENCE.md and examples to EXAMPLES.md.
|
|
25
|
+
- Keep supporting files inside the skill directory so each skill works when installed separately. Link [TROUBLESHOOTING.md](TROUBLESHOOTING.md); the generator copies shared recovery instructions into each skill root.
|
|
26
|
+
|
|
27
|
+
## Keep it current
|
|
28
|
+
|
|
29
|
+
Facts that exist in source (tool names and parameters, REST endpoints, env vars, connect adapters, hook events) are generated, never hand-typed. Edit the source, then run `npm run skills:gen`. CI runs `npm run skills:check` and fails on drift, so generated tables cannot fall behind the code.
|
|
30
|
+
|
|
31
|
+
## Style
|
|
32
|
+
|
|
33
|
+
No external or competitor product names. No emojis. No em-dashes. No filler. State the thing and stop.
|
|
34
|
+
|
|
35
|
+
## Checklist
|
|
36
|
+
|
|
37
|
+
- Description has a "Use when" sentence with real triggers.
|
|
38
|
+
- SKILL.md is under 100 lines.
|
|
39
|
+
- No time-sensitive claims and no duplicated troubleshooting block.
|
|
40
|
+
- Concrete example present; generated facts come from the generator.
|
|
41
|
+
- Cross-links resolve and go one level deep.
|
|
@@ -0,0 +1,70 @@
|
|
|
1
|
+
<!-- AUTOGEN:troubleshooting START - generated by scripts/skills/generate.ts, do not edit by hand -->
|
|
2
|
+
# Troubleshooting agentmemory skills
|
|
3
|
+
|
|
4
|
+
Recovery steps for separately installed skills. This document is generated into
|
|
5
|
+
each skill directory so native skill readers can open it without parent traversal.
|
|
6
|
+
|
|
7
|
+
## "MCP tool not available"
|
|
8
|
+
|
|
9
|
+
Missing tools can mean a stopped MCP process, a disconnected daemon, or an
|
|
10
|
+
explicitly reduced tool surface. Walk these in order:
|
|
11
|
+
|
|
12
|
+
1. Identify the host. In Claude Code, inspect `/plugin list` and `/mcp`.
|
|
13
|
+
In Hermes, inspect the configured memory provider and `mcp_servers` separately.
|
|
14
|
+
In OpenClaw, validate the host configuration and inspect its MCP servers and
|
|
15
|
+
native plugins separately. In Pi or OMP, inspect `/agentmemory-status` and the
|
|
16
|
+
MCP inventory separately; native save/search does not prove the broader tools
|
|
17
|
+
are connected. Do not run another host's setup commands.
|
|
18
|
+
2. Restart or reload the affected host connection after configuration changes.
|
|
19
|
+
3. Inspect the connected tool inventory. Hermes may namespace MCP tools; invoke
|
|
20
|
+
the actual advertised names and schemas. A native memory provider is not
|
|
21
|
+
proof that every MCP tool or shared skill is available.
|
|
22
|
+
4. Check `agentmemory status` and the daemon's `AGENTMEMORY_TOOLS` setting.
|
|
23
|
+
Codex's bundled bridge lists the daemon's enabled tools. The standalone shim
|
|
24
|
+
used by other hosts can fall back to seven basic tools with a separate store.
|
|
25
|
+
Do not claim full daemon functionality based on those seven tools.
|
|
26
|
+
5. If `agentmemory connect codex` and the Codex plugin are both enabled, choose
|
|
27
|
+
one MCP connection. Check `/hooks` before adding global hook fallbacks.
|
|
28
|
+
|
|
29
|
+
Hermes, OpenClaw, Pi and OMP connector installations bundle skills; other hosts
|
|
30
|
+
may install them separately. Check the host's skill inventory and open this file
|
|
31
|
+
from the installed skill directory. Test automatic capture with a real turn and
|
|
32
|
+
a recorded observation; tool connectivity alone does not establish lifecycle
|
|
33
|
+
capture.
|
|
34
|
+
|
|
35
|
+
An outage or timeout is not an empty search result. Report the failure. A write
|
|
36
|
+
may have committed before the response was lost; inspect state before retrying.
|
|
37
|
+
|
|
38
|
+
## REST fallback
|
|
39
|
+
|
|
40
|
+
When the MCP tools stay unavailable but the daemon is running, call the REST
|
|
41
|
+
API directly:
|
|
42
|
+
|
|
43
|
+
1. Set `AGENTMEMORY_URL` to the daemon base URL (default `http://localhost:3111`).
|
|
44
|
+
2. The REST API requires a bearer credential by default. Use the host's explicit
|
|
45
|
+
`AGENTMEMORY_SECRET`; for loopback URLs only, fall back to the secret in
|
|
46
|
+
`~/.agentmemory/.env` and then `~/.agentmemory/secret`. Load the value locally
|
|
47
|
+
without displaying it. Never send a local-file secret to a remote URL.
|
|
48
|
+
If `AGENTMEMORY_CREDENTIAL_MODE=explicit`, require the explicit host credential
|
|
49
|
+
and do not read local credential files.
|
|
50
|
+
Authenticated REST fallback requests require HTTPS for non-loopback
|
|
51
|
+
URLs; HTTP is allowed for loopback URLs (`localhost`, `127.0.0.0/8`, or `[::1]`).
|
|
52
|
+
Reject redirects on authenticated requests. Do not print or save the secret.
|
|
53
|
+
|
|
54
|
+
Endpoint map by skill:
|
|
55
|
+
|
|
56
|
+
| Skill | REST call |
|
|
57
|
+
| --------------- | --------------------------------------------------------------- |
|
|
58
|
+
| remember | `POST /agentmemory/remember` |
|
|
59
|
+
| recall | `POST /agentmemory/smart-search` |
|
|
60
|
+
| recap | `GET /agentmemory/sessions` + `POST /agentmemory/smart-search` |
|
|
61
|
+
| handoff | `GET /agentmemory/sessions` + `POST /agentmemory/smart-search` |
|
|
62
|
+
| session-history | `GET /agentmemory/sessions` |
|
|
63
|
+
| commit-context | `GET /agentmemory/session/by-commit?sha=<sha>` |
|
|
64
|
+
| commit-history | `GET /agentmemory/commits` (URL-encode every query param) |
|
|
65
|
+
|
|
66
|
+
The MCP host reads the plugin MCP configuration. Restart the daemon after
|
|
67
|
+
changing its configuration, then restart or reconnect the host MCP process after
|
|
68
|
+
changing its URL or explicit secret. The local bridge reads the credential files
|
|
69
|
+
for each request; it does not inherit other daemon `.env` settings.
|
|
70
|
+
<!-- AUTOGEN:troubleshooting END -->
|
|
@@ -0,0 +1,190 @@
|
|
|
1
|
+
Apache License
|
|
2
|
+
Version 2.0, January 2004
|
|
3
|
+
http://www.apache.org/licenses/
|
|
4
|
+
|
|
5
|
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
|
6
|
+
|
|
7
|
+
1. Definitions.
|
|
8
|
+
|
|
9
|
+
"License" shall mean the terms and conditions for use, reproduction,
|
|
10
|
+
and distribution as defined by Sections 1 through 9 of this document.
|
|
11
|
+
|
|
12
|
+
"Licensor" shall mean the copyright owner or entity authorized by
|
|
13
|
+
the copyright owner that is granting the License.
|
|
14
|
+
|
|
15
|
+
"Legal Entity" shall mean the union of the acting entity and all
|
|
16
|
+
other entities that control, are controlled by, or are under common
|
|
17
|
+
control with that entity. For the purposes of this definition,
|
|
18
|
+
"control" means (i) the power, direct or indirect, to cause the
|
|
19
|
+
direction or management of such entity, whether by contract or
|
|
20
|
+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
|
21
|
+
outstanding shares, or (iii) beneficial ownership of such entity.
|
|
22
|
+
|
|
23
|
+
"You" (or "Your") shall mean an individual or Legal Entity
|
|
24
|
+
exercising permissions granted by this License.
|
|
25
|
+
|
|
26
|
+
"Source" form shall mean the preferred form for making modifications,
|
|
27
|
+
including but not limited to software source code, documentation
|
|
28
|
+
source, and configuration files.
|
|
29
|
+
|
|
30
|
+
"Object" form shall mean any form resulting from mechanical
|
|
31
|
+
transformation or translation of a Source form, including but
|
|
32
|
+
not limited to compiled object code, generated documentation,
|
|
33
|
+
and conversions to other media types.
|
|
34
|
+
|
|
35
|
+
"Work" shall mean the work of authorship, whether in Source or
|
|
36
|
+
Object form, made available under the License, as indicated by a
|
|
37
|
+
copyright notice that is included in or attached to the work
|
|
38
|
+
(an example is provided in the Appendix below).
|
|
39
|
+
|
|
40
|
+
"Derivative Works" shall mean any work, whether in Source or Object
|
|
41
|
+
form, that is based on (or derived from) the Work and for which the
|
|
42
|
+
editorial revisions, annotations, elaborations, or other modifications
|
|
43
|
+
represent, as a whole, an original work of authorship. For the purposes
|
|
44
|
+
of this License, Derivative Works shall not include works that remain
|
|
45
|
+
separable from, or merely link (or bind by name) to the interfaces of,
|
|
46
|
+
the Work and Derivative Works thereof.
|
|
47
|
+
|
|
48
|
+
"Contribution" shall mean any work of authorship, including
|
|
49
|
+
the original version of the Work and any modifications or additions
|
|
50
|
+
to that Work or Derivative Works thereof, that is intentionally
|
|
51
|
+
submitted to the Licensor for inclusion in the Work by the copyright owner
|
|
52
|
+
or by an individual or Legal Entity authorized to submit on behalf of
|
|
53
|
+
the copyright owner. For the purposes of this definition, "submitted"
|
|
54
|
+
means any form of electronic, verbal, or written communication sent
|
|
55
|
+
to the Licensor or its representatives, including but not limited to
|
|
56
|
+
communication on electronic mailing lists, source code control systems,
|
|
57
|
+
and issue tracking systems that are managed by, or on behalf of, the
|
|
58
|
+
Licensor for the purpose of discussing and improving the Work, but
|
|
59
|
+
excluding communication that is conspicuously marked or otherwise
|
|
60
|
+
designated in writing by the copyright owner as "Not a Contribution."
|
|
61
|
+
|
|
62
|
+
"Contributor" shall mean Licensor and any individual or Legal Entity
|
|
63
|
+
on behalf of whom a Contribution has been received by the Licensor and
|
|
64
|
+
subsequently incorporated within the Work.
|
|
65
|
+
|
|
66
|
+
2. Grant of Copyright License. Subject to the terms and conditions of
|
|
67
|
+
this License, each Contributor hereby grants to You a perpetual,
|
|
68
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
|
69
|
+
copyright license to reproduce, prepare Derivative Works of,
|
|
70
|
+
publicly display, publicly perform, sublicense, and distribute the
|
|
71
|
+
Work and such Derivative Works in Source or Object form.
|
|
72
|
+
|
|
73
|
+
3. Grant of Patent License. Subject to the terms and conditions of
|
|
74
|
+
this License, each Contributor hereby grants to You a perpetual,
|
|
75
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
|
76
|
+
(except as stated in this section) patent license to make, have made,
|
|
77
|
+
use, offer to sell, sell, import, and otherwise transfer the Work,
|
|
78
|
+
where such license applies only to those patent claims licensable
|
|
79
|
+
by such Contributor that are necessarily infringed by their
|
|
80
|
+
Contribution(s) alone or by combination of their Contribution(s)
|
|
81
|
+
with the Work to which such Contribution(s) was submitted. If You
|
|
82
|
+
institute patent litigation against any entity (including a
|
|
83
|
+
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
|
84
|
+
or a Contribution incorporated within the Work constitutes direct
|
|
85
|
+
or contributory patent infringement, then any patent licenses
|
|
86
|
+
granted to You under this License for that Work shall terminate
|
|
87
|
+
as of the date such litigation is filed.
|
|
88
|
+
|
|
89
|
+
4. Redistribution. You may reproduce and distribute copies of the
|
|
90
|
+
Work or Derivative Works thereof in any medium, with or without
|
|
91
|
+
modifications, and in Source or Object form, provided that You
|
|
92
|
+
meet the following conditions:
|
|
93
|
+
|
|
94
|
+
(a) You must give any other recipients of the Work or
|
|
95
|
+
Derivative Works a copy of this License; and
|
|
96
|
+
|
|
97
|
+
(b) You must cause any modified files to carry prominent notices
|
|
98
|
+
stating that You changed the files; and
|
|
99
|
+
|
|
100
|
+
(c) You must retain, in the Source form of any Derivative Works
|
|
101
|
+
that You distribute, all copyright, patent, trademark, and
|
|
102
|
+
attribution notices from the Source form of the Work,
|
|
103
|
+
excluding those notices that do not pertain to any part of
|
|
104
|
+
the Derivative Works; and
|
|
105
|
+
|
|
106
|
+
(d) If the Work includes a "NOTICE" text file as part of its
|
|
107
|
+
distribution, then any Derivative Works that You distribute must
|
|
108
|
+
include a readable copy of the attribution notices contained
|
|
109
|
+
within such NOTICE file, excluding any notices that do not
|
|
110
|
+
pertain to any part of the Derivative Works, in at least one
|
|
111
|
+
of the following places: within a NOTICE text file distributed
|
|
112
|
+
as part of the Derivative Works; within the Source form or
|
|
113
|
+
documentation, if provided along with the Derivative Works; or,
|
|
114
|
+
within a display generated by the Derivative Works, if and
|
|
115
|
+
wherever such third-party notices normally appear. The contents
|
|
116
|
+
of the NOTICE file are for informational purposes only and
|
|
117
|
+
do not modify the License. You may add Your own attribution
|
|
118
|
+
notices within Derivative Works that You distribute, alongside
|
|
119
|
+
or as an addendum to the NOTICE text from the Work, provided
|
|
120
|
+
that such additional attribution notices cannot be construed
|
|
121
|
+
as modifying the License.
|
|
122
|
+
|
|
123
|
+
You may add Your own copyright statement to Your modifications and
|
|
124
|
+
may provide additional or different license terms and conditions
|
|
125
|
+
for use, reproduction, or distribution of Your modifications, or
|
|
126
|
+
for any such Derivative Works as a whole, provided Your use,
|
|
127
|
+
reproduction, and distribution of the Work otherwise complies with
|
|
128
|
+
the conditions stated in this License.
|
|
129
|
+
|
|
130
|
+
5. Submission of Contributions. Unless You explicitly state otherwise,
|
|
131
|
+
any Contribution intentionally submitted for inclusion in the Work
|
|
132
|
+
by You to the Licensor shall be under the terms and conditions of
|
|
133
|
+
this License, without any additional terms or conditions.
|
|
134
|
+
Notwithstanding the above, nothing herein shall supersede or modify
|
|
135
|
+
the terms of any separate license agreement you may have executed
|
|
136
|
+
with Licensor regarding such Contributions.
|
|
137
|
+
|
|
138
|
+
6. Trademarks. This License does not grant permission to use the trade
|
|
139
|
+
names, trademarks, service marks, or product names of the Licensor,
|
|
140
|
+
except as required for reasonable and customary use in describing the
|
|
141
|
+
origin of the Work and reproducing the content of the NOTICE file.
|
|
142
|
+
|
|
143
|
+
7. Disclaimer of Warranty. Unless required by applicable law or
|
|
144
|
+
agreed to in writing, Licensor provides the Work (and each
|
|
145
|
+
Contributor provides its Contributions) on an "AS IS" BASIS,
|
|
146
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
|
147
|
+
implied, including, without limitation, any warranties or conditions
|
|
148
|
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
|
149
|
+
PARTICULAR PURPOSE. You are solely responsible for determining the
|
|
150
|
+
appropriateness of using or redistributing the Work and assume any
|
|
151
|
+
risks associated with Your exercise of permissions under this License.
|
|
152
|
+
|
|
153
|
+
8. Limitation of Liability. In no event and under no legal theory,
|
|
154
|
+
whether in tort (including negligence), contract, or otherwise,
|
|
155
|
+
unless required by applicable law (such as deliberate and grossly
|
|
156
|
+
negligent acts) or agreed to in writing, shall any Contributor be
|
|
157
|
+
liable to You for damages, including any direct, indirect, special,
|
|
158
|
+
incidental, or consequential damages of any character arising as a
|
|
159
|
+
result of this License or out of the use or inability to use the
|
|
160
|
+
Work (including but not limited to damages for loss of goodwill,
|
|
161
|
+
work stoppage, computer failure or malfunction, or any and all
|
|
162
|
+
other commercial damages or losses), even if such Contributor
|
|
163
|
+
has been advised of the possibility of such damages.
|
|
164
|
+
|
|
165
|
+
9. Accepting Warranty or Additional Liability. While redistributing
|
|
166
|
+
the Work or Derivative Works thereof, You may choose to offer,
|
|
167
|
+
and charge a fee for, acceptance of support, warranty, indemnity,
|
|
168
|
+
or other liability obligations and/or rights consistent with this
|
|
169
|
+
License. However, in accepting such obligations, You may act only
|
|
170
|
+
on Your own behalf and on Your sole responsibility, not on behalf
|
|
171
|
+
of any other Contributor, and only if You agree to indemnify,
|
|
172
|
+
defend, and hold each Contributor harmless for any liability
|
|
173
|
+
incurred by, or claims asserted against, such Contributor by reason
|
|
174
|
+
of your accepting any such warranty or additional liability.
|
|
175
|
+
|
|
176
|
+
END OF TERMS AND CONDITIONS
|
|
177
|
+
|
|
178
|
+
Copyright 2026 Rohit Ghumare
|
|
179
|
+
|
|
180
|
+
Licensed under the Apache License, Version 2.0 (the "License");
|
|
181
|
+
you may not use this file except in compliance with the License.
|
|
182
|
+
You may obtain a copy of the License at
|
|
183
|
+
|
|
184
|
+
http://www.apache.org/licenses/LICENSE-2.0
|
|
185
|
+
|
|
186
|
+
Unless required by applicable law or agreed to in writing, software
|
|
187
|
+
distributed under the License is distributed on an "AS IS" BASIS,
|
|
188
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
189
|
+
See the License for the specific language governing permissions and
|
|
190
|
+
limitations under the License.
|