chat-recall 0.6.9 → 0.7.0
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/README.md +2 -2
- package/dist/cli.js +785 -1185
- package/dist/cli.js.map +1 -1
- package/dist/escalate.js +2 -2
- package/dist/escalate.js.map +1 -1
- package/dist/mcp-relay.js +1 -1
- package/dist/mcp.js +2392 -2317
- package/dist/scan-worker.js +4 -5
- package/dist/watch.js +598 -1026
- package/package.json +1 -1
- package/skills/chat-recall/SKILL.md +2 -1
- package/skills/chat-recall-memory/SKILL.md +15 -0
package/README.md
CHANGED
|
@@ -19,7 +19,7 @@
|
|
|
19
19
|
Every coding agent you run keeps a full transcript of its work: the decisions, the
|
|
20
20
|
reasoning, the keys somebody pasted, the problems it found and never filed. Each one
|
|
21
21
|
writes to its own directory in its own format, none can read another's, and nothing
|
|
22
|
-
reads any of them. `chat-recall` does, through **
|
|
22
|
+
reads any of them. `chat-recall` does, through **63 MCP tools**.
|
|
23
23
|
|
|
24
24
|
| | What it does | Tools |
|
|
25
25
|
|---|---|---|
|
|
@@ -131,7 +131,7 @@ Exclusions live on the machine that holds the data, so the CLI owns them; they a
|
|
|
131
131
|
## Four things it actually does
|
|
132
132
|
|
|
133
133
|
1. **Cross-tool unified memory.** One index, one search, one UI over Claude Code (`~/.claude/projects/`), Codex (`~/.codex/`), OpenCode (`~/.local/share/opencode/`), Antigravity (`~/.gemini/antigravity-cli/`) and Cursor (`~/.cursor/` for the CLI, `~/.config/Cursor/` for the IDE). Sessions, plans, tasks, CLAUDE.md files, paste cache, shell history and agent diaries all share one pluggable `MemorySource` interface.
|
|
134
|
-
2. **The agent recalls itself.**
|
|
134
|
+
2. **The agent recalls itself.** 63 MCP tools, so Claude Code can `recall_smart_resume`, `recall_search` (with `like_session` to find similar work), `recall_edits_timeline`, `recall_subagent_search` and `recall_redundant_files` rather than asking you what happened last time. It writes back too, via `recall_decision_record`, `recall_kg_add` and `recall_set`.
|
|
135
135
|
3. **Warns before you redo work.** A `UserPromptSubmit` hook searches for similar past sessions on every prompt and injects a short "you have done this before, in session X" note into the agent's context.
|
|
136
136
|
4. **Temporal knowledge graph.** Decisions and tool mentions become entity-relationship triples with `valid_from`/`valid_to` windows, so you can ask what was decided in March and whether it still holds.
|
|
137
137
|
|