MCP servers and skills: search, filter by where they run, and compare.
Nothing matches every word exactly, so these are the closest matches.
The memory your AI should have had from the start. Automatic capture, automatic recall, 100% local. One SQLite file, zero cloud. Works with Claude Code, Claude CLI, Cursor, Codex CLI, Gemini CLI.
PythonAGPL-3.0★ 382No key
The retrieval stack matters — but ragweld’s differentiator is the engineering surface area around it: benchmarking, evaluation, diagnosis, and operations. It’s built for senior engineers who need answ
SkillGPL-3.0★ 5No key
Hybrid RAG (DuckDB vector + BM25 + RRF + recency/keyword priors + optional cross-encoder rerank) as an installable library + CLI.
PythonAGPL-3.0★ 9No key
Open-source causal graph memory for AI agents. 85.55 on LoCoMo under a frozen, reproducible protocol. MCP server with ACT-R scoring, spreading activation, and active forgetting.
PythonAGPL-3.0★ 31No key
Local-first MCP policy proxy. Tool-block, SQL-mutation gate, PII redact, audit, rate-limit, OpenTelemetry, vault secrets, first-use quarantine, schema pre-inject. No hosted gateway. One YAML Lens wrap
Node.jsAGPL-3.0★ 32No key
Verified memory for AI agents: gated writes, provenance on every read, bi-temporal history, abstention instead of hallucination. AGPL/commercial.
PythonAGPL-3.0★ 4Few starsNo key
Token-efficient MCP doc-router — one canonical doc per query for your coding agents.
PythonAGPL-3.0★ 11No key
Give any MCP-capable agent persistent memory: remember/recall over a tiered store with hybrid vector + keyword retrieval. Single Go binary, SQLite or Postgres, embedded admin UI.
GoAGPL-3.0★ 31No key
Lite version of the BMLibrarian project - does not depend on running local models for inference, and does not depend on large database installations. Requires internet
PythonAGPL-3.0★ 4Few starsNo key
Security-first, memory-frugal vector database in Rust with a retro terminal cockpit.
SkillAGPL-3.0★ 4Few starsNo key
Governed graph-native agent memory: knowledge extraction, fusion, hybrid RAG, scoped access tokens. A push for data sovereignty.
Node.jsAGPL-3.0★ 7Needs a key
Self-hosted AI memory server for Claude, ChatGPT, Codex, Cursor and local LLMs — user-owned storage, human approval gates.
PythonAGPL-3.0Few starsNo key
The knowledge base AI coding agents share. Submit, search, and reuse battle-tested solutions across teams. Self-hosted, MCP-native, AGPL-3.0.
SkillAGPL-3.0★ 5No key
MiroFish-derived skill-native simulation for Codex and Claude with local temporal memory and no project-initiated generation API
SkillAGPL-3.0Few starsNo key
A high-performance MCP (Model Context Protocol) vector database implemented in Erlang/OTP, designed to take full advantage of the Actor model and OTP supervision trees for fault-tolerant, concurrent v
SkillGPL-3.0Few starsNo key
Who stands behind it
