Long-term memory for AI agents — a local-first, agent-native PKM MCP server (provenance, token budgets, hybrid/semantic search, transactional write-back).
claude mcp add tacitus -- npx -y @dashiro/tacitus-mcp-server{
"mcpServers": {
"tacitus": {
"command": "npx",
"args": ["-y", "@dashiro/tacitus-mcp-server"]
}
}
}Resumen de MCP Servers
# Tacitus
**Long-term memory for your AI agents — local-first, with provenance.**
[](https://www.npmjs.com/package/@dashiro/tacitus-mcp-server)
[](https://github.com/ionasrobert/tacitus-mcp-server/actions/workflows/ci.yml)
[](./LICENSE)
Tacitus is an [MCP](https://modelcontextprotocol.io) server that turns any folder
of Markdown notes into an **agent-native knowledge base**. It gives AI agents
(Claude Code, Claude Desktop, and any MCP client) three things they actually need:
1. **Memory with provenance** — typed, queryable long-term memory. Every fact
carries its source and is returned within a token budget; contradictions are
surfaced, not silently resolved.
2. **Retrieval that fits the context window** — search returns ranked snippets
(never whole notes) under a token budget; `get_note` discloses progressively
(outline → frontmatter → full); the wikilink graph is a queryable API.
Hybrid lexical + semantic search, with an optional neural embedder.
3. **Safe write-back** — propose a changeset, preview the diff, commit
atomically, and revert by version. Read-only scope forbids mutations; every
write is audited.
Notes stay as plain `.md` files in your folder. No cloud, no lock-in.
## Quick start
```bash
npx -y @dashiro/tacitus-mcp-server /path/to/your/vault
```
### Claude Code
```bash
claude mcp add tacitus -- npx -y @dashiro/tacitus-mcp-server /path/to/your/vault
```
### Claude Desktop (`claude_desktop_config.json`)
```json
{
"mcpServers": {
"tacitus": {
"command": "npx",
"args": ["-y", "@dashiro/tacitus-mcp-server", "/path/to/your/vault"]
}
}
}
```
## Tools
| Group | Tools |
|---|---|
| **Memory** | `remember`, `recall`, `forget` |
| **Retrieval** | `search`, `get_note`, `graph_query`, `list_notes` |
| **Write-back** | `propose_changes`, `commit_changes`, `revert` |
| **Convenience** | `create_note`, `update_note`, `link`, `tag`, `audit_log` |
| **Meta** | `capabilities` |
Every tool validates input with a schema and returns structured, actionable
errors (`{ code, reason, suggestion }`) rather than stack traces.
## Semantic search (optional neural embeddings)
`search` defaults to **hybrid** mode (lexical + a deterministic, offline
embedder that catches morphological variants). For synonym/paraphrase matching,
opt into a neural embedder:
```bash
npm i @huggingface/transformers
TACITUS_EMBEDDER=transformers npx @dashiro/tacitus-mcp-server /path/to/vault
```
Vectors are cached under `.tacitus/vectors/`. Falls back to the deterministic
embedder if the optional dependency or model isn't available.
## How it stores things
```
your-vault/
├── notes... ← your Markdown files (untouched format)
└── .tacitus/
├── memory/*.md ← agent memories (Markdown + YAML frontmatter)
├── vectors/*.json ← cached embeddings
├── history/*.json ← version snapshots (for revert)
└── audit.log ← JSONL log of every agent write
```
## Development
Polyglot monorepo. The reference server (shipped on npm) is TypeScript in
`packages/mcp-server`. A **native Rust server** in `crates/` is being ported for a
single-binary, zero-runtime-deps build (`crates/tacitus-core` engine +
`crates/tacitus-mcp` rmcp server). Its `stable_id` matches the TS engine
byte-for-byte, so memory ids are identical across both engines.
```bash
# TypeScript server
npm ci
npm test # vitest
npm run typecheck
npm run lint
npm run build # tsup → packages/mcp-server/dist
npm run eval # retrieval quality report
# Rust server (native, single binary)
cargo test
cargo clippy --all-targets -- -D warnings
cargo fmt --check
cargo run -p tacitus-mcp -- /path/to/vault # runs the memory MCP server on stdio
cargo build --release # → target/release/tacitus-mcp
```
The Rust server currently exposes the memory tools (`remember`, `recall`,
`forget`); retrieval and write-back tools are being ported next.
## License
MIT — see [LICENSE](./LICENSE).
Lo que la gente pregunta sobre tacitus-mcp-server
¿Qué es ionasrobert/tacitus-mcp-server?
+
ionasrobert/tacitus-mcp-server es mcp servers para el ecosistema de Claude AI. Long-term memory for AI agents — a local-first, agent-native PKM MCP server (provenance, token budgets, hybrid/semantic search, transactional write-back). Tiene 0 estrellas en GitHub y se actualizó por última vez today.
¿Cómo se instala tacitus-mcp-server?
+
Puedes instalar tacitus-mcp-server clonando el repositorio (https://github.com/ionasrobert/tacitus-mcp-server) o siguiendo las instrucciones del README en GitHub. ClaudeWave también te ofrece bloques de instalación rápida en esta misma página.
¿Es seguro usar ionasrobert/tacitus-mcp-server?
+
ionasrobert/tacitus-mcp-server aún no ha sido auditado por nuestro agente de seguridad. Revisa el repositorio original en GitHub antes de usarlo en producción.
¿Quién mantiene ionasrobert/tacitus-mcp-server?
+
ionasrobert/tacitus-mcp-server es mantenido por ionasrobert. La última actividad registrada en GitHub es de today, con 0 issues abiertos.
¿Hay alternativas a tacitus-mcp-server?
+
Sí. En ClaudeWave puedes explorar mcp servers similares en /categories/mcp, ordenados por popularidad o actividad reciente.
Despliega tacitus-mcp-server en tu cloud
Lleva este repo a producción en minutos. Cada plataforma genera su propio entorno con variables de entorno editables.
¿Mantienes este repo? Añade un badge a tu README
Pega el badge en tu README de GitHub para mostrar que está auditado por ClaudeWave. Cada badge enlaza de vuelta a esta página y muestra el Trust Score actual.
[](https://claudewave.com/repo/ionasrobert-tacitus-mcp-server)<a href="https://claudewave.com/repo/ionasrobert-tacitus-mcp-server"><img src="https://claudewave.com/api/badge/ionasrobert-tacitus-mcp-server" alt="Featured on ClaudeWave: ionasrobert/tacitus-mcp-server" width="320" height="64" /></a>Más MCP Servers
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
An open-source AI agent that brings the power of Gemini directly into your terminal.
The fastest path to AI-powered full stack observability, even for lean teams.
Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface
🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl!