docmind-mcp 0.3.0

package/.env.example

@@ -0,0 +1,12 @@
+# digmunk MCP server configuration
+# 默认知识库根目录（也可在每次工具调用时用 root 参数覆盖）
+DIGMUNK_ROOT=/path/to/your/docs
+
+# Sirchmunk serve 地址
+SIRCHMUNK_URL=http://127.0.0.1:8584
+
+# research 超时（秒）
+DIGMUNK_RESEARCH_TIMEOUT=120
+
+# zg 超时（秒）
+DIGMUNK_SEARCH_TIMEOUT=30

package/README.md

@@ -0,0 +1,109 @@
+# docmind
+
+**Local Deep Research knowledge base for coding agents.**
+
+Point docmind at any folder of documents. Your agent gets three MCP tools:
+
+| Tool | What it does | Cost |
+|------|-------------|------|
+| `search` | Instant hybrid retrieval (BM25 + vectors + ripgrep) | Free, sub-second |
+| `research` | Budgeted LLM deep-dive with source citations, auto-saved as a knowledge note | LLM tokens |
+| `remember` | Persist a fact/decision/summary into the knowledge base | Free |
+
+**The flywheel:** every `research` conclusion is saved and indexed, so tomorrow's `search` answers instantly what today's `research` had to work for.
+
+## Quick start
+
+Single self-contained package (~180 KB, zero npm dependencies — everything runs locally):
+
+```bash
+# Step 1 — install (or `npx docmind-mcp init` to skip installing)
+npm install -g docmind-mcp
+
+# Step 2 — one wizard sets up everything and wires your agent
+docmind init
+```
+
+`docmind init` walks you through everything (about 5 minutes, most of it waiting for downloads):
+
+1. **Dependencies** — detects and installs `zvec-grep`, `ripgrep-all`, CPU-only pytorch, and `sirchmunk` (avoids the 3-4GB CUDA download trap)
+2. **Knowledge folder** — any folder you choose; markdown, PDFs, docx, code, whatever you have
+3. **LLM credentials** — paste `key`, `base url`, and `model` in any format, e.g.:
+
+   ```
+   key=sk-xxx Base url=https://api.example.com/v1 Model name=my-model
+   ```
+
+4. **Service start** — launches the research engine in the background
+5. **Agent integration** — registers the MCP server into your coding agent (optional, interactive)
+
+After init, your agent immediately has `search` / `research` / `remember`. Verify anytime with `docmind doctor`.
+
+## Connect your agent
+
+```bash
+docmind install                # auto-tries opencode, claude-code, codex
+docmind install --target opencode
+docmind install --target claude-code
+docmind install --target codex
+docmind install --target generic   # prints the JSON for any other agent
+```
+
+Manual registration, if you prefer — the MCP server is a plain stdio process:
+
+```json
+{ "docmind": { "command": "docmind-mcp", "env": { "DOCMIND_ROOT": "/path/to/your/docs" } } }
+```
+
+## Everyday commands
+
+```bash
+docmind status          # is the research engine up?
+docmind doctor          # full health check of the whole chain
+docmind up / down       # start / stop the background research engine
+docmind search "query"  # quick terminal search, no agent needed
+docmind index           # rebuild the search index after bulk-importing files
+```
+
+## How your agent uses it
+
+- *"Where is X documented?"* → `search` (free, instant)
+- *"Summarize / compare / explain why..."* → `research` (LLM budget, saves the conclusion)
+- *"Remember this: ..."* → `remember` (teaches your knowledge base)
+
+Each tool call accepts an optional `root` parameter to target a different folder — one docmind instance can serve multiple knowledge bases.
+
+## How it works
+
+```
+Agent ──MCP stdio── docmind
+                     ├── search   → zvec-grep (BM25 + vectors + ripgrep, local index in <root>/.zvec-grep)
+                     ├── research → Sirchmunk (budgeted LLM evidence exploration, http://127.0.0.1:8584)
+                     └── remember → markdown notes in <root>/.knowledge/ (frontmatter-tagged, git-friendly)
+```
+
+- Retrieval is fully local; only `research` calls your LLM, with a hard token budget per query.
+- Knowledge notes are plain markdown — readable, editable, versionable.
+- Hidden folders (`.zvec-grep/`, `.knowledge/`) are indexed for search but excluded from research scans.
+
+## Configuration
+
+| File | Purpose |
+|------|---------|
+| `~/.docmind/config.json` | default knowledge root, service URL, timeouts |
+| `~/.sirchmunk/.env` | `LLM_API_KEY`, `LLM_BASE_URL`, `LLM_MODEL_NAME` |
+
+Environment variables (`DOCMIND_ROOT`, `SIRCHMUNK_URL`) override config values.
+
+## Requirements
+
+- Node.js >= 18.17
+- Python 3.10+ with pip (for the research engine)
+- Linux x64 or macOS (automatic ripgrep-all install currently covers linux/x64; on macOS run `brew install ripgrep-all`)
+
+## Sources
+
+Built on two Apache-2.0 engines:
+
+- [zvec-grep](https://github.com/zvec-ai/zvec-grep) — local hybrid retrieval
+- [Sirchmunk](https://github.com/modelscope/sirchmunk) — indexless agentic search (LENS)