From 4021ffc1a64d1a362cd5ebed24a41835ca7c09f1 Mon Sep 17 00:00:00 2001 From: Drew Botwinick Date: Fri, 25 Sep 2026 12:16:14 -0500 Subject: [PATCH 1/4] Update MCP tool counts to 28 default and 40 full TOOL_PROFILES in memorylayer-mcp-typescript/src/tools.ts now enables 28 tools in the default cc profile (session checkpoints and context packs/deltas were added) and 40 in full, but the root, MCP server and OpenCode plugin READMEs still said 25 and 38, and the cc profile comment said 17. --- README.md | 6 +++--- memorylayer-mcp-typescript/README.md | 8 ++++---- memorylayer-mcp-typescript/src/tools.ts | 7 +++++-- memorylayer-opencode-plugin/README.md | 2 +- 4 files changed, 13 insertions(+), 10 deletions(-) diff --git a/README.md b/README.md index 47876ce..2d53c51 100644 --- a/README.md +++ b/README.md @@ -39,7 +39,7 @@ with sync_client() as memory: - **Document ingestion** -- upload PDFs / DOCX / images and turn them into memories; optional ColPali multi-vector page search via the embed-server peer - **Repository Planning Graph** -- sync code structure, traverse symbols and dependencies, maintain task overlays, and detect file/symbol conflicts - **Skills + MCP registries** -- workspace-scoped libraries of agent skills and MCP server entries with 4-tier scope precedence (user / workspace / tenant / global) -- **MCP integration** -- first-class Model Context Protocol server (25 tools by default, 38 in the `full` profile) for Claude Code, Claude Desktop, OpenCode, Cursor, and other MCP-compatible tools +- **MCP integration** -- first-class Model Context Protocol server (28 tools by default, 40 in the `full` profile) for Claude Code, Claude Desktop, OpenCode, Cursor, and other MCP-compatible tools - **Optional Aether transport** -- run behind an [Aether](https://aetherlayer.ai) mesh for mTLS, signed identity headers, on-behalf-of delegation, durable task scheduling, and cross-datacenter routing ## Packages @@ -51,7 +51,7 @@ with sync_client() as memory: | **[memorylayer-embed-server](./memorylayer-embed-server)** | `pip install "memorylayer-embed-server[local]"` | Stateless embedding peer. `[local]` = CPU (sentence-transformers + ColPali); `[gpu]` adds vLLM, OCR, transcription | | **[memorylayer-sdk-python](./memorylayer-sdk-python)** | `pip install memorylayer-client` | Python client SDK (async/sync, optional Aether transport) | | **[memorylayer-sdk-typescript](./memorylayer-sdk-typescript)** | `npm i @scitrera/memorylayer-sdk` | TypeScript/JavaScript client SDK | -| **[memorylayer-mcp-typescript](./memorylayer-mcp-typescript)** | `npm i @scitrera/memorylayer-mcp-server` | MCP server -- 25 tools (default), up to 38 in `full` | +| **[memorylayer-mcp-typescript](./memorylayer-mcp-typescript)** | `npm i @scitrera/memorylayer-mcp-server` | MCP server -- 28 tools (default), up to 40 in `full` | | **[memorylayer-sdk-langchain-python](./memorylayer-sdk-langchain-python)** | `pip install memorylayer-langchain` | LangChain integration | | **[memorylayer-sdk-llamaindex-python](./memorylayer-sdk-llamaindex-python)** | `pip install memorylayer-llamaindex` | LlamaIndex integration | | **[memorylayer-cc-plugin](./memorylayer-cc-plugin)** | see README | Claude Code plugin -- captures memory before compaction | @@ -201,7 +201,7 @@ Add `.mcp.json` to your project root: } ``` -The MCP server auto-detects your workspace from the git repo name. Claude gets 25 tools by default (38 in the `full` profile) -- remember, recall, reflect, sessions, context sandbox / RLM, chat threads, and skills/MCP-server registry helpers. +The MCP server auto-detects your workspace from the git repo name. Claude gets 28 tools by default (40 in the `full` profile) -- remember, recall, reflect, sessions, checkpoints and context packs, context sandbox / RLM, chat threads, and skills/MCP-server registry helpers. For the full Claude Code experience, also install the **[MemoryLayer plugin](./memorylayer-cc-plugin)** which adds pre-compaction memory capture, session briefings, and automatic memory triggers: diff --git a/memorylayer-mcp-typescript/README.md b/memorylayer-mcp-typescript/README.md index cb761e9..aa15708 100644 --- a/memorylayer-mcp-typescript/README.md +++ b/memorylayer-mcp-typescript/README.md @@ -2,7 +2,7 @@ TypeScript MCP (Model Context Protocol) server for [MemoryLayer.ai](https://memorylayer.ai). -Provides 25 memory tools by default (38 in the `full` profile) for LLM agents to store, recall, synthesize, and manage information across sessions. +Provides 28 memory tools by default (40 in the `full` profile) for LLM agents to store, recall, synthesize, and manage information across sessions. ## Installation @@ -112,8 +112,8 @@ Tools are organized into profiles selected via `MEMORYLAYER_TOOL_PROFILE`: | Profile | Count | Description | |---------|-------|-------------| -| `cc` *(default)* | 25 | Optimized for Claude Code: core memory + sessions + context environment + chat threads + skills (read) | -| `full` | 38 | All tools: adds `associate`, `statistics`, `graph_query`, `audit`, `chat_thread_decompose`, `chat_thread_delete`, `skills_save`, and the 5 `mcp_servers_*` tools | +| `cc` *(default)* | 28 | Optimized for Claude Code: core memory + sessions (including checkpoints and context packs/deltas) + context environment + chat threads + skills (read) | +| `full` | 40 | All tools: adds `associate`, `statistics`, `graph_query`, `audit`, `chat_thread_decompose`, `chat_thread_delete`, `skills_save`, and the 5 `mcp_servers_*` tools | | `minimal` | 2 | Just `memory_remember` and `memory_recall` | > `memory_statistics` and `memory_audit` ship as **placeholders** in the current build; their handlers return `not_implemented` server-side. @@ -403,7 +403,7 @@ The MCP server wraps the `@scitrera/memorylayer-sdk` TypeScript SDK, providing a memorylayer-mcp-typescript/ ├── src/ │ ├── types.ts # TypeScript types for MCP tools -│ ├── tools.ts # MCP tool definitions (25 in cc / 38 in full) +│ ├── tools.ts # MCP tool definitions (28 in cc / 40 in full) │ ├── client.ts # Wrapper around @scitrera/memorylayer-sdk │ ├── session.ts # Local session state management │ ├── workspace.ts # Workspace ID auto-detection diff --git a/memorylayer-mcp-typescript/src/tools.ts b/memorylayer-mcp-typescript/src/tools.ts index 6ab1542..f5ac8ae 100644 --- a/memorylayer-mcp-typescript/src/tools.ts +++ b/memorylayer-mcp-typescript/src/tools.ts @@ -1140,11 +1140,14 @@ export const TOOL_PROFILES: Record = { /** * Claude Code profile (DEFAULT) * - * 17 tools optimized for the Claude Code use case: + * 28 tools optimized for the Claude Code use case: * - Core: remember, recall, reflect, forget - * - Session: session_start, session_end, session_commit, session_status + * - Session: session_start, session_end, session_commit, session_status, + * session_checkpoint, context_pack, context_delta * - Utility: briefing * - Context Environment: exec, inspect, load, inject, query, rlm, status, checkpoint + * - Chat history: thread create, append, get, list + * - Skills (read): list, get, get_file, search * * Excluded (available in "full" profile): * - associate: Graph building is advanced, rarely used without guidance diff --git a/memorylayer-opencode-plugin/README.md b/memorylayer-opencode-plugin/README.md index 69f1f0d..8752989 100644 --- a/memorylayer-opencode-plugin/README.md +++ b/memorylayer-opencode-plugin/README.md @@ -136,7 +136,7 @@ Override with the `MEMORYLAYER_WORKSPACE_ID` environment variable. ``` OpenCode ├── MCP Server (@scitrera/memorylayer-mcp-server) -│ └── 25 memory tools by default (38 in `full` profile) +│ └── 28 memory tools by default (40 in `full` profile) │ ├── Plugin Hooks (@scitrera/memorylayer-opencode-plugin) │ ├── system.transform → session briefing injection From 1237bd007bb98155b2f64912b211ed832201db9c Mon Sep 17 00:00:00 2001 From: Drew Botwinick Date: Fri, 25 Sep 2026 12:16:24 -0500 Subject: [PATCH 2/4] Correct embed-server install, licensing and default bind docs memorylayer-embed-server is container-only (versions.yaml excludes it from the PyPI publish lane), so pip install "memorylayer-embed-server[...]" fails. Point users at the ghcr.io image or a pip install from a repository checkout, and fix the core README's embed CLI name (memorylayer-embed). Also: the visual tokenizer extension is the AGPL-3.0 memorylayer-embed-server-enterprise plugin in scitrera/memorylayer-enterprise, not a proprietary package; MEMORYLAYER_EMBED_SERVER_HOST defaults to 0.0.0.0, not 127.0.0.1; and drop the stale "lockstep with 0.1.22" version note. --- CHANGELOG.md | 3 ++- README.md | 11 ++++---- memorylayer-core-python/README.md | 14 ++++++----- memorylayer-embed-server/README.md | 25 +++++++++++++------ .../docs/embedding-providers.md | 12 ++++----- memorylayer-embed-server/pyproject.toml | 7 +++--- 6 files changed, 43 insertions(+), 29 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 85f1bc4..f8e738a 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -133,7 +133,8 @@ and perspective layer under recall, and a retrieval-quality gate in CI. `sentence_transformers`** (`all-MiniLM-L6-v2`, 384-d, CPU) instead of `vllm_subprocess` (`Qwen3-VL-Embedding-2B`, 2048-d, GPU). Running the embed server no longer requires a GPU, a CUDA toolchain, or a 2B-parameter download. Install with - the new `local` extra: `pip install "memorylayer-embed-server[local]"`. **GPU + the new `local` extra: `pip install "./memorylayer-embed-server[local]"` from a + repository checkout (the embed server is not published to PyPI). **GPU deployments must now set `MEMORYLAYER_EMBED_SINGLE_VECTOR_PROVIDER=vllm_subprocess` explicitly** — and note this changes the vector dimension, which is a property of stored data (see below). diff --git a/README.md b/README.md index 2d53c51..279d0ac 100644 --- a/README.md +++ b/README.md @@ -48,7 +48,7 @@ with sync_client() as memory: |------------------------------------------------------------------------------|---------|---------------------------------------------------------| | **[memorylayer-core-python](./memorylayer-core-python)** | `pip install memorylayer-server` | FastAPI server with SQLite + sqlite-vec storage; optional Turso/libSQL backend | | **[memorylayer-server-rpg-python](./memorylayer-server-rpg-python)** | `pip install memorylayer-server-rpg` | Repository Planning Graph plugin: sync, traversal, overlays, conflicts, maintenance, and enrichment | -| **[memorylayer-embed-server](./memorylayer-embed-server)** | `pip install "memorylayer-embed-server[local]"` | Stateless embedding peer. `[local]` = CPU (sentence-transformers + ColPali); `[gpu]` adds vLLM, OCR, transcription | +| **[memorylayer-embed-server](./memorylayer-embed-server)** | Container image, or `pip install "./memorylayer-embed-server[local]"` from a checkout (not on PyPI) | Stateless embedding peer. `[local]` = CPU (sentence-transformers + ColPali); `[gpu]` adds vLLM, OCR, transcription | | **[memorylayer-sdk-python](./memorylayer-sdk-python)** | `pip install memorylayer-client` | Python client SDK (async/sync, optional Aether transport) | | **[memorylayer-sdk-typescript](./memorylayer-sdk-typescript)** | `npm i @scitrera/memorylayer-sdk` | TypeScript/JavaScript client SDK | | **[memorylayer-mcp-typescript](./memorylayer-mcp-typescript)** | `npm i @scitrera/memorylayer-mcp-server` | MCP server -- 28 tools (default), up to 40 in `full` | @@ -83,8 +83,9 @@ matches on shared words, which is enough to try the API but not for real retriev quality. The server says so in its startup log. When you want real embeddings: ```bash -# Self-hosted on CPU — no GPU, no API key -pip install "memorylayer-embed-server[local]" && memorylayer-embed serve --port 61051 & +# Self-hosted on CPU — no GPU, no API key (embed-server is not on PyPI: +# install it from a checkout of this repo, or run ghcr.io/scitrera/memorylayer-embed-server) +pip install "./memorylayer-embed-server[local]" && memorylayer-embed serve --port 61051 & export MEMORYLAYER_EMBEDDING_PROVIDER=embed_server export MEMORYLAYER_EMBED_SERVER_URL=http://localhost:61051 export MEMORYLAYER_EMBEDDING_DIMENSIONS=384 # must match the embed model @@ -96,8 +97,8 @@ export MEMORYLAYER_EMBEDDING_PROVIDER=openai # or google export MEMORYLAYER_EMBEDDING_OPENAI_API_KEY=sk-... memorylayer serve -# Self-hosted on GPU — adds vLLM, OCR, transcription -pip install "memorylayer-embed-server[gpu]" && memorylayer-embed serve --port 61051 & +# Self-hosted on GPU — adds vLLM, OCR, transcription (or the latest-cuda13 image) +pip install "./memorylayer-embed-server[gpu]" && memorylayer-embed serve --port 61051 & ``` The CPU option downloads `all-MiniLM-L6-v2` (~90 MB, 384-d) on first use and runs diff --git a/memorylayer-core-python/README.md b/memorylayer-core-python/README.md index 3838f60..ec7d471 100644 --- a/memorylayer-core-python/README.md +++ b/memorylayer-core-python/README.md @@ -27,9 +27,10 @@ pip install memorylayer-server[openai] # With Google GenAI embeddings pip install memorylayer-server[google] -# Self-hosted embeddings: install + run memorylayer-embed-server separately -# (no extras here — the main server only speaks HTTP to embed-server) -# pip install memorylayer-embed-server[gpu] +# Self-hosted embeddings: run memorylayer-embed-server separately (container +# image, or install from a repository checkout — it is not on PyPI; no extras +# here — the main server only speaks HTTP to embed-server) +# pip install "./memorylayer-embed-server[gpu]" # All cloud embedding providers + LLM + document parsers pip install memorylayer-server[all] @@ -258,9 +259,10 @@ process or container; the main server only speaks HTTP to it. This is what the published Docker image is pinned to: ```bash -# In a GPU-equipped peer: -pip install memorylayer-embed-server[gpu] -memorylayer-embed-server serve --port 61051 +# In a GPU-equipped peer (from a repository checkout; or run the +# ghcr.io/scitrera/memorylayer-embed-server:latest-cuda13 image): +pip install "./memorylayer-embed-server[gpu]" +memorylayer-embed serve --port 61051 # In the main server process: export MEMORYLAYER_EMBEDDING_PROVIDER=embed_server diff --git a/memorylayer-embed-server/README.md b/memorylayer-embed-server/README.md index 345c7ba..8dfa9f7 100644 --- a/memorylayer-embed-server/README.md +++ b/memorylayer-embed-server/README.md @@ -6,22 +6,31 @@ The main `memorylayer-server` core no longer ships any in-process embedding mode ## Installation +`memorylayer-embed-server` is not published to PyPI. Run the container image, or +install it from a checkout of this repository. + ```bash +# Container: CPU image (latest) or CUDA 13 image (latest-cuda13) +docker run -p 61051:61051 ghcr.io/scitrera/memorylayer-embed-server:latest + +# From a repository checkout +git clone https://github.com/scitrera/memorylayer.git && cd memorylayer + # Local / CPU: sentence-transformers single-vector embeddings (the default provider) -pip install "memorylayer-embed-server[local]" +pip install "./memorylayer-embed-server[local]" # Core install (server skeleton only — no embedding backend) -pip install memorylayer-embed-server +pip install ./memorylayer-embed-server # GPU bundle: OCR + vLLM + ColPali -pip install "memorylayer-embed-server[gpu]" +pip install "./memorylayer-embed-server[gpu]" # Everything: local + GPU + Google embeddings + observability -pip install "memorylayer-embed-server[all]" +pip install "./memorylayer-embed-server[all]" ``` The default single-vector provider is `sentence_transformers`, which needs the -`local` extra. A bare `pip install memorylayer-embed-server` gives you the server +`local` extra. A bare install without extras gives you the server skeleton with no embedding backend; it starts, but logs an error naming the extra to install. Pick a different backend with `MEMORYLAYER_EMBED_SINGLE_VECTOR_PROVIDER` (see [Configuration](#configuration)). @@ -40,7 +49,7 @@ Optional extras: | `all` | `local + gpu + google + observability` | | `dev` | pytest + ruff | -Visual-tokenizer (Qwen3.5) lives in the proprietary `memorylayer-embed-server-enterprise` package; install that separately if you need it. +The Qwen3.5 visual tokenizer lives in the AGPL-3.0 `memorylayer-embed-server-enterprise` plugin in [scitrera/memorylayer-enterprise](https://github.com/scitrera/memorylayer-enterprise); install it alongside this package if you need it. ## Quick Start @@ -91,7 +100,7 @@ Global flag `-v` / `--verbose` enables debug logging. | Variable | Default | Description | |----------|---------|-------------| -| `MEMORYLAYER_EMBED_SERVER_HOST` | `127.0.0.1` | Bind address | +| `MEMORYLAYER_EMBED_SERVER_HOST` | `0.0.0.0` | Bind address (set `127.0.0.1` to accept local connections only) | | `MEMORYLAYER_EMBED_SERVER_PORT` | `61051` | Listening port | | `MEMORYLAYER_EMBED_SINGLE_VECTOR_PROVIDER` | `sentence_transformers` | `sentence_transformers` (local/CPU, 384-d), `vllm_subprocess` (GPU, 2048-d), `vllm` (in-process), `openai`, `google`, `colpali`, `mock`. **Changing this changes the vector dimension — see [Embedding dimensions](#embedding-dimensions).** | | `MEMORYLAYER_EMBEDDING_MODEL` | `sentence-transformers/all-MiniLM-L6-v2` | Single-vector model for the active provider | @@ -188,7 +197,7 @@ The Docker image's healthcheck targets `/health`. ## Versioning -This package is released in lockstep with `memorylayer-server` (currently `0.1.22`). The version pin in `dependencies` keeps client and server protocol versions aligned. +This package is versioned alongside `memorylayer-server`; the exact `memorylayer-server==` pin in `dependencies` keeps client and server protocol versions aligned. ## License diff --git a/memorylayer-embed-server/docs/embedding-providers.md b/memorylayer-embed-server/docs/embedding-providers.md index 26377d2..9ec6269 100644 --- a/memorylayer-embed-server/docs/embedding-providers.md +++ b/memorylayer-embed-server/docs/embedding-providers.md @@ -134,7 +134,7 @@ export MEMORYLAYER_EMBED_USE_MOCK_PROVIDERS=true * Model load is lazy, guarded by a lock (concurrent first requests load once, not N times), and hoisted to startup by `MEMORYLAYER_EMBED_PRELOAD_MODELS=true` (the default). -* Requires the `[local]` extra (`pip install "memorylayer-embed-server[local]"`). +* Requires the `[local]` extra (`pip install "./memorylayer-embed-server[local]"`). Because this is the *default* provider, a bare install with no extra is the most likely first-run failure — the log names the exact install command rather than raising a bare `ImportError` traceback. @@ -172,7 +172,7 @@ Swapping the model changes the vector width (e.g. `all-mpnet-base-v2` is * Multimodal: supports image embedding via the `{"prompt": "...", "multi_modal_data": {"image": }}` prompt shape, so models like `Qwen/Qwen3-VL-Embedding-2B` are first-class. -* Requires the `[vllm]` extra (`pip install memorylayer-embed-server[vllm]`) +* Requires the `[vllm]` extra (`pip install "./memorylayer-embed-server[vllm]"`) and a CUDA-capable host. `Dockerfile.real-test-full` installs this. **Env knobs**: @@ -346,7 +346,7 @@ Requires installing the OSS server with the `google` extra (`qwen2.5` → ColQwen2.5, `qwen2` → ColQwen2, `modernvbert` → ColModernVBert, `colpali` → original ColPali). Defaults to ColModernVBert (MIT-licensed, smallest). -* Requires the `[colpali]` extra (`pip install memorylayer-embed-server[colpali]`) +* Requires the `[colpali]` extra (`pip install "./memorylayer-embed-server[colpali]"`) which pulls in `colpali-engine` + `torch`. GPU strongly recommended. **Env knobs**: @@ -471,7 +471,7 @@ multi-vector endpoints will 503. ### Observability -Install with `pip install memorylayer-embed-server[observability]` +Install with `pip install "./memorylayer-embed-server[observability]"` (or `[all]`). The embed-server reuses the OSS server's pluggable `MetricsService` and `OTelInitPlugin`. @@ -568,7 +568,7 @@ config keys are documented separately. ### Local / CPU quick start (no GPU, real embeddings) ```bash -pip install "memorylayer-embed-server[local]" +pip install "./memorylayer-embed-server[local]" memorylayer-embed serve ``` @@ -592,7 +592,7 @@ a GPU. ### Fully GPU-free, single **and** multi vector ```bash -pip install "memorylayer-embed-server[local,colpali]" +pip install "./memorylayer-embed-server[local,colpali]" ``` ``` diff --git a/memorylayer-embed-server/pyproject.toml b/memorylayer-embed-server/pyproject.toml index 0d53ddf..9d46bec 100644 --- a/memorylayer-embed-server/pyproject.toml +++ b/memorylayer-embed-server/pyproject.toml @@ -31,7 +31,8 @@ dependencies = [ [project.optional-dependencies] # Local/CPU single-vector embeddings (sentence-transformers, all-MiniLM-L6-v2). # This backs the DEFAULT single-vector provider, so it is what a local install -# needs: pip install "memorylayer-embed-server[local]". Kept an extra rather than +# needs: pip install "./memorylayer-embed-server[local]" from a repository +# checkout (the package is not on PyPI). Kept an extra rather than # a base dependency because it pulls torch, and deployments that only use the # openai/google passthrough should not pay for that. local = ["sentence-transformers>=3.0.0", "torch>=2.11.0,<2.12.0"] @@ -57,8 +58,8 @@ observability = [ ] gpu = ["memorylayer-embed-server[ocr,vllm,colpali]"] all = ["memorylayer-embed-server[local,gpu,google,observability]"] -# Visual-tokenizer (Qwen3.5) lives in the proprietary -# memorylayer-embed-server-enterprise package; install that separately. +# Visual-tokenizer (Qwen3.5) lives in the AGPL-3.0 memorylayer-embed-server-enterprise +# plugin (scitrera/memorylayer-enterprise); install that separately. dev = [ "pytest>=9.0.2", "pytest-asyncio>=1.3.0", From 6671b3b5ed13d452f3a47b1aac90c7a77cb98c42 Mon Sep 17 00:00:00 2001 From: Drew Botwinick Date: Fri, 25 Sep 2026 12:16:24 -0500 Subject: [PATCH 3/4] Document the OpenClaw skills sync directory and extraDirs requirement The README said skills are materialized into /skills and need no openclaw.json change. skills-sync.ts writes to a dedicated /.memorylayer-skills (or MEMORYLAYER_SKILLS_DIR), which OpenClaw only discovers once it is listed in skills.load.extraDirs. --- memorylayer-openclaw-plugin/README.md | 30 +++++++++++++++------------ 1 file changed, 17 insertions(+), 13 deletions(-) diff --git a/memorylayer-openclaw-plugin/README.md b/memorylayer-openclaw-plugin/README.md index f1e0f14..043c18f 100644 --- a/memorylayer-openclaw-plugin/README.md +++ b/memorylayer-openclaw-plugin/README.md @@ -44,29 +44,33 @@ The sandbox-provider sets these when launching the OpenClaw container: | `WORKCLAW_DEFAULT_WORKSPACE` | no | Default MemoryLayer workspace id | | `WORKCLAW_GRANT_ID` | no | Default Aether grant id (sets default OBO authority) | | `MEMORYLAYER_SKILLS_SYNC` | no | `1`/`true` to materialize MemoryLayer skills into OpenClaw (default OFF) | +| `MEMORYLAYER_SKILLS_DIR` | no | Absolute path of the managed skills dir (default: `/.memorylayer-skills`) | ## Skills sync (opt-in) When `MEMORYLAYER_SKILLS_SYNC=1`, on each agent bootstrap the plugin fetches the principal's **enabled** MemoryLayer skills and calls the SDK's -`client.skills.materialize(...)` to write each `SKILL.md` + its files into the -agent workspace skills directory (`/skills`). OpenClaw already -scans **and** watches that directory, so the materialized skills are discovered -and hot-reloaded natively — MemoryLayer is the source of truth, OpenClaw the -local cache. The sync is best-effort: errors are logged and never block agent -bootstrap. - -Because `/skills` is a dir OpenClaw watches by default, **no -`openclaw.json` change is required**. If a deployment ever materializes into a -non-default directory instead, that directory must be declared so OpenClaw scans -it, via one line in the rendered `openclaw.json`: +`client.skills.materialize(...)` to write each `SKILL.md` + its files into a +dedicated, MemoryLayer-only skills directory: `/.memorylayer-skills` +by default, or the absolute path in `MEMORYLAYER_SKILLS_DIR` when set. +MemoryLayer is the source of truth and OpenClaw the local cache. The sync is a +reconcile: after a successful listing, skills that were disabled, deleted or +renamed in MemoryLayer are pruned from that directory (never after a failed +listing). It is best-effort: errors are logged and never block agent bootstrap. + +The plugin deliberately does not write into the shared `/skills` +directory, which also holds user-authored, plugin and bundled skills that a +reconcile would clobber. Because the managed directory is not one OpenClaw scans +by default, it **must be declared** in `skills.load.extraDirs` in the rendered +`openclaw.json`, using the same path the plugin writes to: ```jsonc -{ "skills": { "load": { "extraDirs": ["/abs/path/to/dir"] } } } +{ "skills": { "load": { "extraDirs": ["/abs/path/to/workspace/.memorylayer-skills"] } } } ``` (The sandbox-provider renders `openclaw.json` in -`internal/openclaw/bootstrap.go`; this plugin does not edit it.) +`internal/openclaw/bootstrap.go` and stamps the same path into both +`MEMORYLAYER_SKILLS_DIR` and `extraDirs`; this plugin does not edit it.) ## OpenClaw integration From 0ea196784b579911ce5dbd52b9f3d27918cf3dc0 Mon Sep 17 00:00:00 2001 From: Drew Botwinick Date: Fri, 25 Sep 2026 12:16:24 -0500 Subject: [PATCH 4/4] Use namespaced slash commands in the Claude Code plugin docs Claude Code namespaces plugin commands as /:. The plugin is named memorylayer and ships commands/{status,setup,remember,recall}.md, so the commands are /memorylayer:status etc.; /memorylayer-status does not exist. --- memorylayer-cc-plugin/README.md | 10 ++++++---- memorylayer-cc-plugin/commands/recall.md | 16 ++++++++-------- memorylayer-cc-plugin/commands/remember.md | 10 +++++----- memorylayer-cc-plugin/commands/setup.md | 4 ++-- memorylayer-cc-plugin/commands/status.md | 6 +++--- 5 files changed, 24 insertions(+), 22 deletions(-) diff --git a/memorylayer-cc-plugin/README.md b/memorylayer-cc-plugin/README.md index dfd2710..f6851e3 100644 --- a/memorylayer-cc-plugin/README.md +++ b/memorylayer-cc-plugin/README.md @@ -115,12 +115,14 @@ Working memory persists within a session and survives context compaction. At ses ### Slash Commands +Claude Code namespaces plugin commands under the plugin name (`memorylayer`), so they run as `/memorylayer:`: + | Command | Description | |---------|-------------| -| `/memorylayer-status` | Check connection and workspace info | -| `/memorylayer-setup` | Guided setup and troubleshooting | -| `/memorylayer-remember ` | Quick memory storage | -| `/memorylayer-recall ` | Quick memory search | +| `/memorylayer:status` | Check connection and workspace info | +| `/memorylayer:setup` | Guided setup and troubleshooting | +| `/memorylayer:remember ` | Quick memory storage | +| `/memorylayer:recall ` | Quick memory search | ### Hooks diff --git a/memorylayer-cc-plugin/commands/recall.md b/memorylayer-cc-plugin/commands/recall.md index 259b819..a0c28ac 100644 --- a/memorylayer-cc-plugin/commands/recall.md +++ b/memorylayer-cc-plugin/commands/recall.md @@ -1,20 +1,20 @@ -# /memorylayer-recall +# /memorylayer:recall Quick command to search memories. ## Usage ``` -/memorylayer-recall +/memorylayer:recall ``` ## Examples ``` -/memorylayer-recall database decisions -/memorylayer-recall authentication bugs -/memorylayer-recall user preferences -/memorylayer-recall what do we know about the API +/memorylayer:recall database decisions +/memorylayer:recall authentication bugs +/memorylayer:recall user preferences +/memorylayer:recall what do we know about the API ``` ## Behavior @@ -50,6 +50,6 @@ No memories found matching "your query" Try: - Broader search terms -- Check /memorylayer-status for connection issues -- Use /memorylayer-remember to store new memories +- Check /memorylayer:status for connection issues +- Use /memorylayer:remember to store new memories ``` diff --git a/memorylayer-cc-plugin/commands/remember.md b/memorylayer-cc-plugin/commands/remember.md index ec87ee0..a9fdffd 100644 --- a/memorylayer-cc-plugin/commands/remember.md +++ b/memorylayer-cc-plugin/commands/remember.md @@ -1,19 +1,19 @@ -# /memorylayer-remember +# /memorylayer:remember Quick command to store a memory. ## Usage ``` -/memorylayer-remember +/memorylayer:remember ``` ## Examples ``` -/memorylayer-remember We decided to use PostgreSQL for better JSON support -/memorylayer-remember The auth bug was caused by missing token refresh -/memorylayer-remember User prefers detailed commit messages +/memorylayer:remember We decided to use PostgreSQL for better JSON support +/memorylayer:remember The auth bug was caused by missing token refresh +/memorylayer:remember User prefers detailed commit messages ``` ## Behavior diff --git a/memorylayer-cc-plugin/commands/setup.md b/memorylayer-cc-plugin/commands/setup.md index 80e28f2..1956577 100644 --- a/memorylayer-cc-plugin/commands/setup.md +++ b/memorylayer-cc-plugin/commands/setup.md @@ -1,11 +1,11 @@ -# /memorylayer-setup +# /memorylayer:setup Automated setup and verification for MemoryLayer. ## Usage ``` -/memorylayer-setup +/memorylayer:setup ``` ## Behavior diff --git a/memorylayer-cc-plugin/commands/status.md b/memorylayer-cc-plugin/commands/status.md index 7f8145f..6dc1021 100644 --- a/memorylayer-cc-plugin/commands/status.md +++ b/memorylayer-cc-plugin/commands/status.md @@ -1,11 +1,11 @@ -# /memorylayer-status +# /memorylayer:status Check MemoryLayer connection status and workspace information. ## Usage ``` -/memorylayer-status +/memorylayer:status ``` ## Behavior @@ -56,5 +56,5 @@ Server: NOT CONNECTED Troubleshooting: 1. Start the server: memorylayer serve 2. Check MEMORYLAYER_URL environment variable -3. Run /memorylayer-setup for guided configuration +3. Run /memorylayer:setup for guided configuration ```