271 MCP servers and agent skills in the Knowledge & Memory category, ranked by quality score.
Local memory layer over the session histories coding agents already write (Claude Code, Codex CLI, opencode): lexical search, recall tools, session-start auto-recall, secret redaction at index time, cross-machine sync over SSH.
Institutional memory for AI agents with real BFT consensus. 4 application validators vote on every memory before it's committed — no more storing garbage. 13 MCP tools, runs locally, works with any MCP-compatible model. Backed by 4 published research papers.
Private-by-default memory and context layer for agents with Go/Rust runtime, staged retrieval across fused data backends, and long-horizon context continuity.
Self-hostable, markdown-native team wiki with a built-in MCP server: agents search, read, and write your wiki pages (ranked Postgres full-text + semantic search, backlink traversal). Plus Atlas, which auto-generates a cited, coverage-checked wiki from your git repos and Jira. Go + Postgres. `npx tela-mcp`
Memory with provenance tracking — records where agent knowledge originated and detects when sources change. 17 MCP tools for session handoffs, decisions, semantic search, and knowledge graph. Works across Claude Code, Cursor, Windsurf, Codex CLI, and Gemini CLI. Single Go binary, SQLite + vector search, fully local.
Connect to any MediaWiki wiki (Wikipedia, Fandom, corporate wikis). 33+ tools for search, read, edit, link analysis, revision history, and Markdown conversion. Supports stdio and HTTP transport.
Persistent memory engine for AI coding agents. Stores architecture decisions, bug root causes, and project conventions across sessions. Single Go binary with embedded SQLite, FTS5 search, context assembly within token budgets, and autopilot setup for Claude Code, Kiro, and Cursor.
LLM-driven context and memory management with wide-recall + precise-reranking RAG architecture. Features multi-dimensional retrieval (vector/timeline/knowledge graph), short/long-term memory, and complete MCP support (HTTP/WebSocket/SSE).
Git-native project memory for coding agents: Markdown source of truth committed to your repo, reviewable staged updates (`review --diff` → `apply`), secret/PII-safe, branch-aware — no cloud, no vector DB.
Local-first developer activity aggregator. Indexes commits, PRs, Jira/Linear tickets, Confluence docs, Slack threads, and Calendar events into SQLite + FTS5 + on-device ONNX embeddings; exposes 15 tools, 3 resources, and 3 prompts so Claude Code, Cursor, and Codex can search and cite your past work. `brew install --cask pavelpilyak/devrecall/devrecall`
Lightweight local RAG MCP server for semantic vector search over markdown documents. Reduces token consumption by 40x with sqlite-vec and multilingual-e5-small embeddings. Supports filtered search by directory and filename patterns.
Zero-dependency MCP memory server. Single binary, 100% local, no Docker.
Local-first semantic search over library docs. Single Go binary, MCP stdio, vector index pinned to the binary version. Like Context7 with the internet off. Pre-built index DB auto-fetched on first launch and SHA256-verified, then zero network. Also available as `docker run --rm -i ghcr.io/laradji/deadzone server`. Listed in the official MCP Registry as `io.github.laradji/deadzone`.
A simple memory tool for coding agents using DuckDB and VoyageAI.