@pcircle/memesh 4.2.8 → 4.2.9
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/.claude-plugin/marketplace.json +1 -1
- package/.claude-plugin/plugin.json +1 -1
- package/README.md +15 -15
- package/dashboard/dist/index.html +5 -5
- package/dist/skills-manifest.json +10 -10
- package/dist/transports/http/server.d.ts.map +1 -1
- package/dist/transports/http/server.js +12 -19
- package/dist/transports/http/server.js.map +1 -1
- package/package.json +1 -1
- package/scripts/hooks/_shared.js +64 -0
- package/scripts/hooks/post-commit.js +25 -46
- package/scripts/hooks/pre-compact.js +9 -32
- package/scripts/hooks/session-summary.js +9 -11
package/README.md
CHANGED
|
@@ -16,22 +16,11 @@
|
|
|
16
16
|
|
|
17
17
|
---
|
|
18
18
|
|
|
19
|
-
|
|
20
|
-
> **Actively developed project** — features evolve and may change between releases. If you hit a bug or have a feature request, please [open an issue](https://github.com/PCIRCLE-AI/memesh-llm-memory/issues).
|
|
21
|
-
|
|
22
|
-
## The Problem
|
|
23
|
-
|
|
24
|
-
Your coding agent forgets what happened between sessions. Every architecture decision, bug fix, failed test, and hard-won lesson has to be re-explained. Claude Code starts fresh, re-discovers old constraints, and burns context on things it should already know.
|
|
25
|
-
|
|
26
|
-
**MeMesh gives coding agents persistent, searchable, evolving local memory.**
|
|
27
|
-
|
|
28
|
-
This package is the local memory layer of the MeMesh product family. It is intentionally small and open-source: install it with npm, keep your memory in `~/.memesh/knowledge-graph.db`, and connect it to Claude Code or any MCP-compatible client. Hosted workspace and enterprise operating-system products should stay separate from this package's README and roadmap.
|
|
29
|
-
|
|
30
|
-
---
|
|
19
|
+
**MeMesh** — the open-source **memory layer** for Claude Code & MCP agents. One SQLite file. No cloud. Plugs into any LLM.
|
|
31
20
|
|
|
32
|
-
##
|
|
21
|
+
## 95.40% R@5 on LongMemEval-S — beats Mem0 by 46 points
|
|
33
22
|
|
|
34
|
-
MeMesh's retrieval
|
|
23
|
+
MeMesh's retrieval is **FTS5 alone** — no LLM, no embeddings on the hot path. Measured against the public [LongMemEval-S](https://huggingface.co/datasets/xiaowu0162/longmemeval) benchmark (500 questions, MIT-licensed):
|
|
35
24
|
|
|
36
25
|
| System | R@5 | Source |
|
|
37
26
|
|---|---|---|
|
|
@@ -41,7 +30,18 @@ MeMesh's retrieval engine is **FTS5 alone** (no LLM, no embeddings on the hot pa
|
|
|
41
30
|
| Zep | 63.8% | LongMemEval paper |
|
|
42
31
|
| Mem0 | 49.0% | LongMemEval paper |
|
|
43
32
|
|
|
44
|
-
|
|
33
|
+
Re-runnable in ~10 seconds. Full instructions, dataset SHA256, raw per-question results, and known-failure analysis: [`benchmarks/longmemeval/REPRODUCE.md`](benchmarks/longmemeval/REPRODUCE.md).
|
|
34
|
+
|
|
35
|
+
---
|
|
36
|
+
|
|
37
|
+
## The Problem
|
|
38
|
+
|
|
39
|
+
Your coding agent forgets between sessions. Every architecture decision, bug fix, failed test, and hard-won lesson has to be re-explained. Claude Code starts fresh, re-discovers old constraints, and burns context on things it should already know.
|
|
40
|
+
|
|
41
|
+
**MeMesh gives coding agents persistent, searchable, evolving local memory.** Install with npm, memory lives in `~/.memesh/knowledge-graph.db`, plug into Claude Code or any MCP-compatible client.
|
|
42
|
+
|
|
43
|
+
> [!IMPORTANT]
|
|
44
|
+
> Actively developed — features may change between releases. [Open an issue](https://github.com/PCIRCLE-AI/memesh-llm-memory/issues) for bugs or feature requests.
|
|
45
45
|
|
|
46
46
|
---
|
|
47
47
|
|