clawmem 0.1.1 → 0.1.2
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 +21 -6
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -8,7 +8,7 @@
|
|
|
8
8
|
|
|
9
9
|
ClawMem fuses recent research into a retrieval-augmented memory layer that agents actually use. The hybrid architecture combines [QMD](https://github.com/tobi/qmd)-derived multi-signal retrieval (BM25 + vector search + reciprocal rank fusion + query expansion + cross-encoder reranking), [SAME](https://github.com/sgx-labs/statelessagent)-inspired composite scoring (recency decay, confidence, content-type half-lives, co-activation reinforcement), [MAGMA](https://arxiv.org/abs/2501.13956)-style intent classification with multi-graph traversal (semantic, temporal, and causal beam search), and [A-MEM](https://arxiv.org/abs/2510.02178) self-evolving memory notes that enrich documents with keywords, tags, and causal links between entries. Pattern extraction from [Engram](https://github.com/Gentleman-Programming/engram) adds deduplication windows, frequency-based durability scoring, and temporal navigation.
|
|
10
10
|
|
|
11
|
-
|
|
11
|
+
Integrates via Claude Code hooks, an MCP server (works with any MCP-compatible client including OpenClaw), or a native OpenClaw ContextEngine plugin. All paths write to the same local SQLite vault. A decision captured during a Claude Code session shows up immediately when an OpenClaw agent picks up the same project.
|
|
12
12
|
|
|
13
13
|
TypeScript on Bun. MIT License.
|
|
14
14
|
|
|
@@ -61,8 +61,21 @@ Runs fully local with no API keys and no cloud services. Integrates via Claude C
|
|
|
61
61
|
|
|
62
62
|
### Prerequisites
|
|
63
63
|
|
|
64
|
-
|
|
65
|
-
|
|
64
|
+
**Required:**
|
|
65
|
+
|
|
66
|
+
- [Bun](https://bun.sh) v1.0+ — runtime for ClawMem
|
|
67
|
+
- SQLite with FTS5 — included with Bun. On macOS, install `brew install sqlite` for extension loading support (ClawMem detects and uses Homebrew SQLite automatically).
|
|
68
|
+
|
|
69
|
+
**Optional (for better performance):**
|
|
70
|
+
|
|
71
|
+
- [llama.cpp](https://github.com/ggml-org/llama.cpp) (`llama-server`) — for dedicated GPU inference. Without it, `node-llama-cpp` runs models in-process (auto-downloads on first use). GPU servers give better throughput and prevent silent CPU fallback.
|
|
72
|
+
- systemd (Linux) or launchd (macOS) — for persistent background services (watcher, embed timer, GPU servers). ClawMem ships systemd unit templates; macOS users can create equivalent launchd plists. See [systemd services](docs/guides/systemd-services.md).
|
|
73
|
+
|
|
74
|
+
**Optional integrations:**
|
|
75
|
+
|
|
76
|
+
- [Claude Code](https://docs.anthropic.com/en/docs/claude-code) — for hooks + MCP integration
|
|
77
|
+
- [OpenClaw](https://github.com/openclawai/openclaw) — for ContextEngine plugin integration
|
|
78
|
+
- [bd CLI](https://github.com/dolthub/dolt) v0.58.0+ — for Beads issue tracker sync (only if using Beads)
|
|
66
79
|
|
|
67
80
|
### Install from npm (recommended)
|
|
68
81
|
|
|
@@ -100,6 +113,8 @@ After installing, here's the full journey from zero to working memory:
|
|
|
100
113
|
|
|
101
114
|
**Fastest path:** Step 1 alone gets you a working system with in-process CPU/GPU inference and default models — no manual model downloads or service configuration needed. Steps 2-4 are optional upgrades for better performance. Steps 5-6 are where you customize what gets indexed and how your agent connects.
|
|
102
115
|
|
|
116
|
+
**Customize what gets indexed:** Each collection has a `pattern` field in `~/.config/clawmem/config.yaml` (default: `**/*.md`). Tailor it per collection — index project docs, research notes, decision records, Obsidian vaults, or anything else your agents should know about. The more relevant content in the vault, the better retrieval works. See the [quickstart](docs/quickstart.md#customize-index-patterns) for config examples.
|
|
117
|
+
|
|
103
118
|
### Quick start commands
|
|
104
119
|
|
|
105
120
|
```bash
|
|
@@ -130,7 +145,7 @@ ClawMem integrates via hooks (`settings.json`) and an MCP stdio server. Hooks ha
|
|
|
130
145
|
|
|
131
146
|
```bash
|
|
132
147
|
clawmem setup hooks # Install lifecycle hooks (SessionStart, UserPromptSubmit, Stop, PreCompact)
|
|
133
|
-
clawmem setup mcp # Register MCP server in ~/.claude.json (
|
|
148
|
+
clawmem setup mcp # Register MCP server in ~/.claude.json (28 tools)
|
|
134
149
|
```
|
|
135
150
|
|
|
136
151
|
**Automatic (90%):** `context-surfacing` injects relevant memory on every prompt. `postcompact-inject` re-injects state after compaction. `decision-extractor`, `handoff-generator`, `feedback-loop` capture session state on stop.
|
|
@@ -157,7 +172,7 @@ Disable OpenClaw's native memory and `memory-lancedb` auto-recall/capture to avo
|
|
|
157
172
|
openclaw config set agents.defaults.memorySearch.extraPaths "[]"
|
|
158
173
|
```
|
|
159
174
|
|
|
160
|
-
**Alternative:**
|
|
175
|
+
**Alternative:** OpenClaw agents can also use ClawMem's MCP server directly (`clawmem setup mcp`), with or without hooks. This gives full access to all 28 MCP tools but bypasses OpenClaw's ContextEngine lifecycle, so you lose token budget awareness, native compaction orchestration, and the `afterTurn()` message pipeline. The ContextEngine plugin is recommended for new OpenClaw setups; MCP is available as an additional or standalone integration.
|
|
161
176
|
|
|
162
177
|
#### Dual-Mode Operation
|
|
163
178
|
|
|
@@ -388,7 +403,7 @@ llama-server -m Qwen3-Reranker-0.6B-Q8_0.gguf \
|
|
|
388
403
|
|
|
389
404
|
### MCP Server
|
|
390
405
|
|
|
391
|
-
ClawMem exposes
|
|
406
|
+
ClawMem exposes 28 MCP tools via the [Model Context Protocol](https://modelcontextprotocol.io) and an optional HTTP REST API. Any MCP-compatible client or HTTP client can use it.
|
|
392
407
|
|
|
393
408
|
**Claude Code (automatic):**
|
|
394
409
|
|