superlocalmemory 4.2.6__tar.gz → 4.2.7__tar.gz

{superlocalmemory-4.2.6/src/superlocalmemory.egg-info → superlocalmemory-4.2.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: superlocalmemory
-Version: 4.2.6
+Version: 4.2.7
 Summary: The governed memory brain for AI agents: one local memory for Claude Code, Codex, Cursor, Copilot, ChatGPT and any MCP client
 Author-email: Varun Pratap Bhardwaj <admin@superlocalmemory.com>
 License-Expression: AGPL-3.0-or-later
@@ -138,6 +138,8 @@ Dynamic: license-file
 
 **[Install](#install)** · **[See it work](#30-second-example)** · **[Full demo](https://www.youtube.com/watch?v=9Y0wAT07KTc)** · **[Every capability](#everything-slm-does)** · **[Docs](#documentation)** · **[Website](https://www.superlocalmemory.com)**
 
+**⭐ If SuperLocalMemory keeps your agents from guessing, [star the repo](https://github.com/qualixar/superlocalmemory/stargazers). It helps other developers find it.**
+
 <img src="https://raw.githubusercontent.com/qualixar/superlocalmemory/main/docs/assets/gifs/recall-tiers.gif" alt="Recall in the dashboard: a real question gets its answer; a gibberish question gets 'That isn't in SuperLocalMemory.'; a real question memory cannot answer exactly gets the closest memories, labelled" width="820">
 
 
@@ -189,6 +191,8 @@ slm connect claude-code
 slm media enable                  # optional: pictures and documents (about 1.5 GB; needs 16 GB of memory)
 ```
 
+**uv**: `uv tool install --python 3.12 superlocalmemory` installs `slm` as an isolated tool, with nothing to activate; see [Linux install](docs/install-linux.md#isolated-slm-command-with-uv).
+
 **Claude Code plugin:** `claude plugin marketplace add qualixar/superlocalmemory`, then `claude plugin install superlocalmemory@qualixar`. **Codex:** `slm connect codex`, then `slm codex install`.
 
 **Two models, one memory.** Text is searched with a small local text model (nomic). If you turn on pictures and documents, a second local model (Google's EmbeddingGemma 2) reads them, and one recall returns both. The picture model unloads after 30 minutes without use, so it holds no memory while you only work with text. Details: [pictures and documents](https://github.com/qualixar/superlocalmemory/blob/main/docs/pictures-and-documents.md), [getting started](https://github.com/qualixar/superlocalmemory/blob/main/docs/getting-started.md), [agent setup steps](https://github.com/qualixar/superlocalmemory/blob/main/SETUP_FOR_AGENTS.md).
@@ -420,7 +424,7 @@ Engineering controls that support a compliance program, not a certification.
 
 ## MCP memory server: tool profiles
 
-Every app, plugin and extension gets `full` (58 tools: all of memory, SLM-Mesh, optimize, loops) unless you choose otherwise. That fits hosts that cap the total number of MCP tools at about 100, with room for your other servers. To change it for every app at once, run one command and restart your apps:
+Every app, plugin and extension gets `full` (58 tools: all of memory, SLM-Mesh, optimize, loops; 5 more while images are on) unless you choose otherwise. That fits hosts that cap the total number of MCP tools at about 100, with room for your other servers. To change it for every app at once, run one command and restart your apps:
 
 ```bash
 slm tools                # current set, and how many tools each set has
@@ -504,7 +508,7 @@ Cite with [CITATION.cff](https://github.com/qualixar/superlocalmemory/blob/main/
 ## Upgrade
 
 ```bash
-npm update -g superlocalmemory    # or: pipx upgrade superlocalmemory
+npm update -g superlocalmemory    # or: pipx upgrade superlocalmemory, uv tool upgrade superlocalmemory
 slm restart && slm doctor
 slm upgrade-hosts                 # preview plugin and IDE updates; nothing changes until you --apply
 ```
@@ -522,6 +526,10 @@ Upgrades never move or delete memory, and a store update takes a restore point f
 
 Python 3.12+, Node 18+ for npm. Pictures and documents need 16 GB of memory.
 
+## Star history
+
+<a href="https://star-history.com/#qualixar/superlocalmemory&Date"><img src="https://api.star-history.com/svg?repos=qualixar/superlocalmemory&type=Date" alt="SuperLocalMemory GitHub star history" width="600"></a>
+
 ## Contributing and license
 
 Issues and pull requests are welcome: [CONTRIBUTING.md](https://github.com/qualixar/superlocalmemory/blob/main/CONTRIBUTING.md). Security reports: [SECURITY.md](https://github.com/qualixar/superlocalmemory/blob/main/SECURITY.md). Licensed under [AGPL-3.0-or-later](https://github.com/qualixar/superlocalmemory/blob/main/LICENSE); for a commercial license see [COMMERCIAL-LICENSE.md](https://github.com/qualixar/superlocalmemory/blob/main/COMMERCIAL-LICENSE.md).

{superlocalmemory-4.2.6 → superlocalmemory-4.2.7}/README.md

@@ -22,6 +22,8 @@
 
 **[Install](#install)** · **[See it work](#30-second-example)** · **[Full demo](https://www.youtube.com/watch?v=9Y0wAT07KTc)** · **[Every capability](#everything-slm-does)** · **[Docs](#documentation)** · **[Website](https://www.superlocalmemory.com)**
 
+**⭐ If SuperLocalMemory keeps your agents from guessing, [star the repo](https://github.com/qualixar/superlocalmemory/stargazers). It helps other developers find it.**
+
 <img src="https://raw.githubusercontent.com/qualixar/superlocalmemory/main/docs/assets/gifs/recall-tiers.gif" alt="Recall in the dashboard: a real question gets its answer; a gibberish question gets 'That isn't in SuperLocalMemory.'; a real question memory cannot answer exactly gets the closest memories, labelled" width="820">
 
 
@@ -73,6 +75,8 @@ slm connect claude-code
 slm media enable                  # optional: pictures and documents (about 1.5 GB; needs 16 GB of memory)
 ```
 
+**uv**: `uv tool install --python 3.12 superlocalmemory` installs `slm` as an isolated tool, with nothing to activate; see [Linux install](docs/install-linux.md#isolated-slm-command-with-uv).
+
 **Claude Code plugin:** `claude plugin marketplace add qualixar/superlocalmemory`, then `claude plugin install superlocalmemory@qualixar`. **Codex:** `slm connect codex`, then `slm codex install`.
 
 **Two models, one memory.** Text is searched with a small local text model (nomic). If you turn on pictures and documents, a second local model (Google's EmbeddingGemma 2) reads them, and one recall returns both. The picture model unloads after 30 minutes without use, so it holds no memory while you only work with text. Details: [pictures and documents](https://github.com/qualixar/superlocalmemory/blob/main/docs/pictures-and-documents.md), [getting started](https://github.com/qualixar/superlocalmemory/blob/main/docs/getting-started.md), [agent setup steps](https://github.com/qualixar/superlocalmemory/blob/main/SETUP_FOR_AGENTS.md).
@@ -304,7 +308,7 @@ Engineering controls that support a compliance program, not a certification.
 
 ## MCP memory server: tool profiles
 
-Every app, plugin and extension gets `full` (58 tools: all of memory, SLM-Mesh, optimize, loops) unless you choose otherwise. That fits hosts that cap the total number of MCP tools at about 100, with room for your other servers. To change it for every app at once, run one command and restart your apps:
+Every app, plugin and extension gets `full` (58 tools: all of memory, SLM-Mesh, optimize, loops; 5 more while images are on) unless you choose otherwise. That fits hosts that cap the total number of MCP tools at about 100, with room for your other servers. To change it for every app at once, run one command and restart your apps:
 
 ```bash
 slm tools                # current set, and how many tools each set has
@@ -388,7 +392,7 @@ Cite with [CITATION.cff](https://github.com/qualixar/superlocalmemory/blob/main/
 ## Upgrade
 
 ```bash
-npm update -g superlocalmemory    # or: pipx upgrade superlocalmemory
+npm update -g superlocalmemory    # or: pipx upgrade superlocalmemory, uv tool upgrade superlocalmemory
 slm restart && slm doctor
 slm upgrade-hosts                 # preview plugin and IDE updates; nothing changes until you --apply
 ```
@@ -406,6 +410,10 @@ Upgrades never move or delete memory, and a store update takes a restore point f
 
 Python 3.12+, Node 18+ for npm. Pictures and documents need 16 GB of memory.
 
+## Star history
+
+<a href="https://star-history.com/#qualixar/superlocalmemory&Date"><img src="https://api.star-history.com/svg?repos=qualixar/superlocalmemory&type=Date" alt="SuperLocalMemory GitHub star history" width="600"></a>
+
 ## Contributing and license
 
 Issues and pull requests are welcome: [CONTRIBUTING.md](https://github.com/qualixar/superlocalmemory/blob/main/CONTRIBUTING.md). Security reports: [SECURITY.md](https://github.com/qualixar/superlocalmemory/blob/main/SECURITY.md). Licensed under [AGPL-3.0-or-later](https://github.com/qualixar/superlocalmemory/blob/main/LICENSE); for a commercial license see [COMMERCIAL-LICENSE.md](https://github.com/qualixar/superlocalmemory/blob/main/COMMERCIAL-LICENSE.md).

{superlocalmemory-4.2.6 → superlocalmemory-4.2.7}/plugin-src/agents/slm-governance-advisor.md

@@ -81,4 +81,4 @@ slm-scope · slm-governance · slm-profile · slm-remember · slm-recall · slm-
 # What NOT to do
 Never session_init twice; never forget without dry-run preview; never run `slm gdpr erase --yes` unasked; never store secrets; never bypass role checks; never claim an erasure succeeded without verifying via recall.
 
-SuperLocalMemory v4.2.6 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v4.2.7 · Qualixar · AGPL-3.0-or-later

{superlocalmemory-4.2.6 → superlocalmemory-4.2.7}/plugin-src/agents/slm-loop-runner.md

@@ -79,4 +79,4 @@ assessment. The gate is the authority.
 
 ---
 
-SuperLocalMemory v4.2.6 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v4.2.7 · Qualixar · AGPL-3.0-or-later

{superlocalmemory-4.2.6 → superlocalmemory-4.2.7}/plugin-src/agents/slm-memory-advisor.md

@@ -51,4 +51,4 @@ slm-recall · slm-remember · slm-session · slm-scope · slm-profile · slm-gov
 # What NOT to do
 Never session_init twice; never forget dry_run=False without reporting preview; never switch the active profile unasked; never dump a whole file into remember; never invent a memory; never claim "saved" without success:true / clean CLI exit; never bypass scope or governance restrictions.
 
-SuperLocalMemory v4.2.6 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v4.2.7 · Qualixar · AGPL-3.0-or-later

{superlocalmemory-4.2.6 → superlocalmemory-4.2.7}/plugin-src/agents/slm-optimize-advisor.md

@@ -41,4 +41,4 @@ slm-compress · slm-cache · slm-status · slm-profile
 # What NOT to do
 Never compress code-for-edit/JSON-to-parse/<500 chars; never store secrets/ccr_ids; never let optimize failure block/alter the task; never claim a specific savings %; never hand a ccr_id to another agent.
 
-SuperLocalMemory v4.2.6 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v4.2.7 · Qualixar · AGPL-3.0-or-later

{superlocalmemory-4.2.6 → superlocalmemory-4.2.7}/plugin-src/rules/AGENTS.md

@@ -187,4 +187,4 @@ Using this memory from a web assistant or another computer: see the slm-web-acce
 - **slm-governance-advisor** — scope/role compliance, retention and lifecycle, GDPR
 - **slm-loop-runner** — bounded, gate-verified loops (the `/slm-loop` command delegates to it)
 
-SuperLocalMemory v4.2.6 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v4.2.7 · Qualixar · AGPL-3.0-or-later

{superlocalmemory-4.2.6 → superlocalmemory-4.2.7}/plugin-src/rules/CLAUDE.md.fragment

@@ -1,4 +1,4 @@
-<!-- BEGIN SuperLocalMemory v4.2.6 -->
+<!-- BEGIN SuperLocalMemory v4.2.7 -->
 
 ## SuperLocalMemory (SLM) — Agent Rules
 
@@ -51,6 +51,6 @@ slm-recall · slm-remember · slm-session · slm-status · slm-cache · slm-comp
 ### Subagents
 slm-memory-advisor (memory decisions, session hygiene, scope/profile guidance) · slm-optimize-advisor (context compression + KV cache) · slm-governance-advisor (scope/roles/compliance/GDPR) · slm-loop-runner (bounded, gate-verified loops)
 
-<!-- END SuperLocalMemory v4.2.6 -->
+<!-- END SuperLocalMemory v4.2.7 -->
 
-SuperLocalMemory v4.2.6 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v4.2.7 · Qualixar · AGPL-3.0-or-later

{superlocalmemory-4.2.6 → superlocalmemory-4.2.7}/plugin-src/skills/slm-bot-memory/SKILL.md

@@ -178,4 +178,4 @@ store every local bot on that computer can reach.
 
 ---
 
-*SuperLocalMemory v4.2.6 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v4.2.7 · Qualixar · AGPL-3.0-or-later*

{superlocalmemory-4.2.6 → superlocalmemory-4.2.7}/plugin-src/skills/slm-cache/SKILL.md

@@ -2,7 +2,7 @@
 name: slm-cache
 description: KV cache for repeated reads — call slm_cache_get(key) first; on a miss do the expensive operation then slm_cache_set(key, value, ttl_seconds) to store it; on a hit use the returned value directly; always fail-open (hit:false on any error, never raises); saves tokens when the same file, query result, or tool output is read more than once in a session.
 when_to_use: "cache file, avoid re-reading, repeated read, cache result, cache tool output, save re-read, reuse across session, cache check, cache hit, cache miss"
-allowed-tools: slm_cache_set, slm_cache_get, Bash
+allowed-tools: slm_cache_set, slm_cache_get, Bash(slm:*)
 ---
 
 # slm-cache — KV Cache for Repeated Reads (Surface B)
@@ -144,4 +144,4 @@ These subcommands control daemon-level cache settings and bulk removal. They do
 
 ---
 
-SuperLocalMemory v4.2.6 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v4.2.7 · Qualixar · AGPL-3.0-or-later

{superlocalmemory-4.2.6 → superlocalmemory-4.2.7}/plugin-src/skills/slm-compress/SKILL.md

@@ -2,7 +2,7 @@
 name: slm-compress
 description: Compress large text, tool output, or transcripts to reduce context-window usage while keeping the full 1M window intact — call slm_compress(content, mode, reversible, ttl_seconds) to shrink content; if the result is lossy a ccr_id is returned so you can call slm_retrieve(ccr_id) later to recover the exact original; always fail-open (ok:false → continue with the original).
 when_to_use: "compress context, shrink output, save tokens, context window full, long transcript, compress tool result, reduce tokens, large output, compress text"
-allowed-tools: slm_compress, slm_retrieve, Bash
+allowed-tools: slm_compress, slm_retrieve, Bash(slm:*)
 ---
 
 # slm-compress — Reversible Context Compression (Surface B)
@@ -147,4 +147,4 @@ Content over 1 MB (1 000 000 bytes UTF-8) is processed but `reversible` is force
 
 ---
 
-SuperLocalMemory v4.2.6 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v4.2.7 · Qualixar · AGPL-3.0-or-later

{superlocalmemory-4.2.6 → superlocalmemory-4.2.7}/plugin-src/skills/slm-getting-started-bot/SKILL.md

@@ -194,4 +194,4 @@ quality on a shared box.
 
 ---
 
-*SuperLocalMemory v4.2.6 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v4.2.7 · Qualixar · AGPL-3.0-or-later*

{superlocalmemory-4.2.6 → superlocalmemory-4.2.7}/plugin-src/skills/slm-governance/SKILL.md

@@ -11,7 +11,7 @@ when_to_use: |
   - "The dashboard asks for a key" (slm token show)
   - Enterprise deployment with multi-team shared SLM
   - Compliance, audit, or data governance task
-allowed-tools: audit_trail, set_retention_policy, get_retention_stats, get_lifecycle_status, compact_memories, consistency_check, recall, search, remember, Bash
+allowed-tools: audit_trail, set_retention_policy, get_retention_stats, get_lifecycle_status, compact_memories, consistency_check, recall, search, remember, Bash(slm:*)
 ---
 
 # slm-governance — Governed Workspace Behavior
@@ -114,7 +114,7 @@ a picture or page only when its text held no secret or personal data.
 
 When login is required, every operation on memories needs a signed-in user,
 including the connection your assistant uses. SLM handles this at the daemon
-level; agents do not pass credentials in tool calls. If a tool call returns an
+level; agents never put credentials in tool calls. If a tool call returns an
 authentication or permission error, you must:
 
 1. Stop the current operation immediately.
@@ -276,4 +276,4 @@ Before running any destructive or state-changing operation (`forget`,
 
 ---
 
-*SuperLocalMemory v4.2.6 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v4.2.7 · Qualixar · AGPL-3.0-or-later*

{superlocalmemory-4.2.6 → superlocalmemory-4.2.7}/plugin-src/skills/slm-graph/SKILL.md

@@ -15,7 +15,7 @@ when_to_use: |
   - code navigation in unfamiliar repos
   - blast radius before a PR
   - pre-commit change detection
-allowed-tools: build_code_graph, query_graph, get_blast_radius, semantic_search_code, get_review_context, detect_changes, Bash
+allowed-tools: build_code_graph, query_graph, get_blast_radius, semantic_search_code, get_review_context, detect_changes, Bash(slm:*)
 ---
 
 # slm-graph — Code Intelligence Skill
@@ -318,4 +318,4 @@ All are host-only: a remote caller cannot use them.
 
 ---
 
-SuperLocalMemory v4.2.6 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v4.2.7 · Qualixar · AGPL-3.0-or-later

{superlocalmemory-4.2.6 → superlocalmemory-4.2.7}/plugin-src/skills/slm-loop/SKILL.md

@@ -2,7 +2,7 @@
 name: slm-loop
 description: Gate-verified bounded loops with SuperLocalMemory as the durable ledger. Use when a task has a checkable acceptance condition and you must iterate until an INDEPENDENT gate passes — never stopping because the agent believes it is done. `slm_loop_run` (MCP) waits, under hard bounds, for an independently executed check registered by the operator to pass; `slm loop demo` shows the control flow keyless; `slm loop history` and `slm loop show <run_id>` (or `slm_loop_history` / `slm_loop_show`) inspect past runs, whose every lap is stored as queryable SLM memory (tag `loop:<name>`). Terminal statuses are DONE / HALT / PAUSE / KILLED / ERROR — report them exactly, never converting HALT/PAUSE/ERROR into success.
 when_to_use: "run a bounded loop, gate-verified task, iterate until tests pass, verify against an independent gate, don't trust the agent's own done claim, slm loop, convergence loop, loop until green, loop ledger, wait for another agent's result"
-allowed-tools: slm_loop_run, slm_loop_history, slm_loop_show, recall, report_outcome, get_soft_prompts, skill_health, skill_lineage, evolve_skill, observe_bounded_loop_evidence, Bash
+allowed-tools: slm_loop_run, slm_loop_history, slm_loop_show, recall, report_outcome, get_soft_prompts, skill_health, skill_lineage, evolve_skill, observe_bounded_loop_evidence, Bash(slm:*)
 ---
 
 # slm-loop — Bounded, gate-verified agent loops
@@ -171,4 +171,4 @@ Guides: `docs/skill-evolution.md`, `docs/bounded-loops-bridge.md`.
 
 ---
 
-SuperLocalMemory v4.2.6 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v4.2.7 · Qualixar · AGPL-3.0-or-later

{superlocalmemory-4.2.6 → superlocalmemory-4.2.7}/plugin-src/skills/slm-media/SKILL.md

@@ -9,7 +9,7 @@ when_to_use: |
   - remember_media, remember_document, get_media, media_status or media_upload_link is missing from the tool list
   - "Turn on pictures and documents", slm media status, slm media repair
   - "Connect my Obsidian vault / notes folder" (slm sources)
-allowed-tools: remember_media, remember_document, get_media, media_status, media_upload_link, recall, Bash
+allowed-tools: remember_media, remember_document, get_media, media_status, media_upload_link, recall, Bash(slm:*)
 ---
 
 # slm-media — Pictures, PDFs and Folders
@@ -337,4 +337,4 @@ minutes (previous vectors are kept) and let them decide.
 
 ---
 
-*SuperLocalMemory v4.2.6 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v4.2.7 · Qualixar · AGPL-3.0-or-later*

{superlocalmemory-4.2.6 → superlocalmemory-4.2.7}/plugin-src/skills/slm-mesh/SKILL.md

@@ -12,7 +12,7 @@ when_to_use: |
   - "Wait for the other bot's reply" (mesh_wait)
   - A web app (ChatGPT, Claude on the web, Grok Bot, Muse, Composio) should message the owner's other bots
   - Messages come back marked repeat, or ack_ids appear in a reply
-allowed-tools: mesh_summary, mesh_peers, mesh_send, mesh_inbox, mesh_wait, mesh_state, mesh_lock, mesh_events, mesh_status, Bash
+allowed-tools: mesh_summary, mesh_peers, mesh_send, mesh_inbox, mesh_wait, mesh_state, mesh_lock, mesh_events, mesh_status, Bash(slm:*)
 ---
 
 # slm-mesh — Cross-Session Peer Coordination
@@ -386,4 +386,4 @@ mesh availability.
 
 ---
 
-*SuperLocalMemory v4.2.6 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v4.2.7 · Qualixar · AGPL-3.0-or-later*

{superlocalmemory-4.2.6 → superlocalmemory-4.2.7}/plugin-src/skills/slm-profile/SKILL.md

@@ -10,7 +10,7 @@ when_to_use: |
   - "Why can't I see tool X?"
   - Multi-project workflows needing memory isolation
   - Switching between personal and team workspaces
-allowed-tools: switch_profile, get_status, Bash
+allowed-tools: switch_profile, get_status, Bash(slm:*)
 ---
 
 # slm-profile — Memory Profiles and Tool Sets
@@ -99,7 +99,7 @@ named differently (for example `superlocalmemory-personal` and
 |---------|-------|------------|
 | `core` | 19 tools — remember, recall, search, fetch, expand, list_recent, update_memory, forget, session, optimize, corrections, summaries, switch_profile | Smallest set |
 | `code` | 39 tools — core + portable Brain evidence, report_outcome/report_feedback, 6 code-graph tools, memory kinds, bounded loops | For coding agents that need the graph; no mesh, no `get_status` |
-| `full` | 58 tools — everyday memory, delete_memory, get_status, observe, saved views, learning tools, skills, optimize, kinds, loops, mesh | The default for every app |
+| `full` | 58 tools (5 more while images are on) — everyday memory, delete_memory, get_status, observe, saved views, learning tools, skills, optimize, kinds, loops, mesh | The default for every app |
 | `power` | 70 tools — full + audit_trail, retention, compaction, consistency_check, behavioral and diagnostic tools | Governance and admin work |
 | `mesh` | 9 tools — mesh coordination only | Lightweight cross-session signalling |
 
@@ -164,4 +164,4 @@ anything but `core` or `mesh`.
 
 ---
 
-*SuperLocalMemory v4.2.6 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v4.2.7 · Qualixar · AGPL-3.0-or-later*

{superlocalmemory-4.2.6 → superlocalmemory-4.2.7}/plugin-src/skills/slm-recall/SKILL.md

@@ -8,7 +8,7 @@ when_to_use: |
   - "Find stored information about authentication / the database / error handling"
   - "Search for what I said about Y"
   - Automatically before any non-trivial task, to surface prior context
-allowed-tools: recall, search, fetch, expand, list_recent, get_memory_summary, run_view, report_outcome, report_feedback, Bash
+allowed-tools: recall, search, fetch, expand, list_recent, get_memory_summary, run_view, report_outcome, report_feedback, Bash(slm:*)
 ---
 
 # slm-recall — Search & Retrieve Memory
@@ -515,4 +515,4 @@ See `slm-profile`.
 
 ---
 
-*SuperLocalMemory v4.2.6 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v4.2.7 · Qualixar · AGPL-3.0-or-later*

{superlocalmemory-4.2.6 → superlocalmemory-4.2.7}/plugin-src/skills/slm-remember/SKILL.md

@@ -8,7 +8,7 @@ when_to_use: |
   - "Note this as a gotcha / blocker / convention"
   - After making a non-obvious decision during a coding session
   - After resolving a bug whose root cause should be persisted
-allowed-tools: remember, recall, update_memory, set_memory_kind, review_memory_kinds, confirm_memory_kinds, list_corrections, review_correction, delete_memory, Bash
+allowed-tools: remember, recall, update_memory, set_memory_kind, review_memory_kinds, confirm_memory_kinds, list_corrections, review_correction, delete_memory, Bash(slm:*)
 ---
 
 # slm-remember — Capture Durable Facts
@@ -372,4 +372,4 @@ sessions on this machine, so use it only when the user asks to move. See
 
 ---
 
-*SuperLocalMemory v4.2.6 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v4.2.7 · Qualixar · AGPL-3.0-or-later*

{superlocalmemory-4.2.6 → superlocalmemory-4.2.7}/plugin-src/skills/slm-scope/SKILL.md

@@ -8,7 +8,7 @@ when_to_use: |
   - "Can other agents on this machine see my memories?"
   - User explicitly asks to cross-profile share a fact or see shared facts
   - Enterprise setup where multiple profiles collaborate
-allowed-tools: remember, recall, search, list_recent, Bash
+allowed-tools: remember, recall, search, list_recent, Bash(slm:*)
 ---
 
 # slm-scope — Memory Scope and Sharing Model
@@ -180,4 +180,4 @@ to review the impact. See `slm-remember` for the full deletion discipline.
 
 ---
 
-*SuperLocalMemory v4.2.6 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v4.2.7 · Qualixar · AGPL-3.0-or-later*

{superlocalmemory-4.2.6 → superlocalmemory-4.2.7}/plugin-src/skills/slm-session/SKILL.md

@@ -6,7 +6,7 @@ when_to_use: |
   - When the user says "start a new session" or "initialize memory"
   - When meaningful work completes and context should be committed
   - When the user says "close session" or "end session"
-allowed-tools: session_init, close_session, Bash
+allowed-tools: session_init, close_session, Bash(slm:*)
 ---
 
 # slm-session — Session Lifecycle Hygiene
@@ -288,4 +288,4 @@ answered. To also surface shared or global facts, call `recall` with
 
 ---
 
-*SuperLocalMemory v4.2.6 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v4.2.7 · Qualixar · AGPL-3.0-or-later*

{superlocalmemory-4.2.6 → superlocalmemory-4.2.7}/plugin-src/skills/slm-status/SKILL.md

@@ -2,7 +2,7 @@
 name: slm-status
 description: Health and optimization stats for SuperLocalMemory — call slm_optimize_stats() for live compression and cache counters (compress_runs, tokens_saved_compress, cache_proxy_hits, cache_proxy_misses, cache_kv_hits, cache_kv_misses); run slm status [--json] for system state (mode, profile, DB size, fact/entity/edge counts) and slm doctor [--json] for preflight including the "Optimize (Surface B)" health line; use together to confirm optimization is actually saving tokens.
 when_to_use: "check slm status, health check, is slm working, optimize stats, tokens saved, cache hits, compress runs, slm doctor, preflight, db size, slm info, diagnose slm, slm media status, are pictures on, slm features, picture search not working, slm media repair, embedder status, memory health, slm enrich, repair memories, undo a repair"
-allowed-tools: slm_optimize_stats, get_status, get_brain_evidence_status, Bash
+allowed-tools: slm_optimize_stats, get_status, get_brain_evidence_status, Bash(slm:*)
 ---
 
 # slm-status — Health and Optimize Stats
@@ -228,4 +228,4 @@ the memory-engine upgrade is pending.
 
 ---
 
-SuperLocalMemory v4.2.6 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v4.2.7 · Qualixar · AGPL-3.0-or-later

{superlocalmemory-4.2.6 → superlocalmemory-4.2.7}/plugin-src/skills/slm-web-access/SKILL.md

@@ -2,7 +2,7 @@
 name: slm-web-access
 description: Set up and troubleshoot SuperLocalMemory Web access, the optional link that lets web apps (ChatGPT, Claude on the web, Muse, Composio, other remote MCP clients) use the memory on this computer. Covers turning it on from the dashboard, adding and removing apps, read/save/session permissions, the second yes for bot messages and pictures (the Web access switches in Connected apps), one-time upload links for pictures and PDFs, what leaves the computer, renewal, the connection states, the errors a web app can see, and the copy-paste instructions for web agents.
 when_to_use: "web access, connected apps, connect chatgpt, connect claude web, connect muse, connect composio, connect grok bot, remote mcp, mcp.superlocalmemory.com, connector_asleep, DAILY_LIMIT_REACHED, web app cannot reach memory, instructions for web agent, web app bot messages, web app upload link, Let these apps message your other bots, Let these apps save and read pictures and documents, not_for_remote"
-allowed-tools: get_status, Read, Bash
+allowed-tools: get_status, Read, Bash(slm:*)
 ---
 
 # slm-web-access — Web apps and bots

{superlocalmemory-4.2.6 → superlocalmemory-4.2.7}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "superlocalmemory"
-version = "4.2.6"
+version = "4.2.7"
 description = "The governed memory brain for AI agents: one local memory for Claude Code, Codex, Cursor, Copilot, ChatGPT and any MCP client"
 readme = "README.md"
 license = "AGPL-3.0-or-later"

{superlocalmemory-4.2.6 → superlocalmemory-4.2.7}/src/superlocalmemory/__init__.py

@@ -32,7 +32,7 @@ if "OMP_NUM_THREADS" not in os.environ:
     os.environ["OMP_NUM_THREADS"] = "2"
 # ---------------------------------------------------------------------------
 
-__version__ = "4.2.6"
+__version__ = "4.2.7"
 
 _REQUIRED_VERSIONS = {
     "sentence_transformers": "5.6.1",

{superlocalmemory-4.2.6 → superlocalmemory-4.2.7}/src/superlocalmemory/cli/commands.py

@@ -648,6 +648,11 @@ def _cmd_upgrade_hosts(args: Namespace) -> None:
     cmd_upgrade_hosts(args)
 
 
+def _cmd_repair_speaker(args: Namespace) -> None:
+    from superlocalmemory.cli.repair_speaker_cmd import cmd_repair_speaker
+    cmd_repair_speaker(args)
+
+
 def dispatch(args: Namespace) -> None:
     """Route CLI command to the appropriate handler."""
     handlers = {
@@ -670,6 +675,7 @@ def dispatch(args: Namespace) -> None:
         "brain": cmd_brain,
         "health": cmd_health,
         "doctor": cmd_doctor,
+        "repair-speaker": _cmd_repair_speaker,
         "trace": cmd_trace,
         "mcp": cmd_mcp,
         "tools": _cmd_tools,
@@ -1946,6 +1952,8 @@ def cmd_remember(args: Namespace) -> None:
         extra = {"preserve_unprocessable": True, "preserve_server_error": sync_mode}
         if replaces is not None:
             body["replaces"] = replaces
+        if (getattr(args, "speaker", "") or "").strip():
+            body["speaker"] = args.speaker.strip()
         body["idempotency_key"] = _cli_remember_idempotency_key(body)
         try:
             result = daemon_request("POST", path, body,
@@ -2235,6 +2243,8 @@ def cmd_recall(args: Namespace) -> None:
                 for note in filter(None, (incomplete, project_line(result), fidelity_line(result),
                                           _answer_check_line(result))):
                     print(f"\n{note}")
+                from superlocalmemory.cli.star_prompt import maybe_print_first_recall_ask
+                maybe_print_first_recall_ask(args, len(result["results"]))
                 return
     except Exception as _exc:  # noqa: BLE001
         logger.warning(
@@ -2964,6 +2974,7 @@ _COMMAND_GROUPS: list[tuple[str, list[tuple[str, str]]]] = [
         ("list", "Show recent memories (-n N)"),
         ("update", "Propose an immutable correction by id"),
         ("review-correction", "Apply, reject, or roll back a correction case"),
+        ("repair-speaker", "Re-derive facts where an agent's \"I\" was saved as the user"),
         ("delete", "Delete a memory by id"),
         ("forget", "Run the decay cycle (preview first)"),
         ("trace", "Recall with a per-channel score breakdown"),
@@ -3140,6 +3151,8 @@ def cmd_help(args: Namespace) -> None:
     print("Topics:              slm help modes | slm help config | "
           "slm help self-heal")
     print("Docs:                https://superlocalmemory.com")
+    from superlocalmemory.cli.star_prompt import print_help_footer
+    print_help_footer()
 
 
 def _migration_error_logs() -> list:

{superlocalmemory-4.2.6 → superlocalmemory-4.2.7}/src/superlocalmemory/cli/main.py

@@ -504,6 +504,10 @@ def main() -> None:
     remember_p = sub.add_parser("remember", help="Store a memory (extracts facts, builds graph)")
     remember_p.add_argument("content", help="Content to remember")
     remember_p.add_argument("--tags", default="", help="Comma-separated tags")
+    remember_p.add_argument(
+        "--speaker", default="",
+        help='Who "I" means in the text (default: you). E.g. --speaker Ava for an agent\'s words',
+    )
     remember_p.add_argument(
         "--kind", default="",
         help="What sort of memory this is: rule, decision, status, procedure, "
@@ -726,6 +730,13 @@ def main() -> None:
         help="Apply --refile-hidden instead of only showing what it would do",
     )
 
+    repair_speaker_p = sub.add_parser(
+        "repair-speaker",
+        help="Re-derive facts where an agent's own \"I\" was saved as the user (dry run; --yes applies)",
+    )
+    repair_speaker_p.add_argument("--yes", action="store_true", help="Apply the repair")
+    repair_speaker_p.add_argument("--json", action="store_true", help="JSON output")
+
     # v3.8.2 super-help — grouped overview of every command + focused topics.
     help_p = sub.add_parser(
         "help",