Workflow and knowledge layer for teams coding with Claude Code. Each session starts with ≤5k chars of repo-scoped context, follows one workflow (orient → grill → epic → build → document), and files ev
Local-first code intelligence over MCP: BM25/FTS5 + AST graph, impact analysis, project memory and safe writes. Text-first by default; optional dense. Works with OpenCode and Zed.
Token-efficient context engine for AI coding agents. v2.23.0: token-killer pack — deep-forget (unlearning propagation), dangling-reference guard, MCP schemas-on-demand. 2462 tests, 43 MCP tools, Ela
Penpal MCP: a local-first memory layer for AI agents on macOS. Gives Claude Code, Codex and Cursor searchable, cited memory of your browsing, clipboard, windows and past AI sessions, with per-agent gr
Knowledge graph of PHP codebases for AI coding agents (Claude Code, Codex, Cursor) over MCP. Static analysis, no LLM.
Deterministic Self-Evolving Meta-Kernel for AI Coding Agents — Offline Git Worktree Evolution, Zero-Dep Deliverable Inspector, AST Cognitive Memory & 5-Tool Meta-MCP Gateway
The self-hosted bureau for AI agents: they get briefed on missions from a durable task queue, file what they learn into a markdown+git brain, and show up for work in a 8-bit Gameboy inspired office.
MCP memory server for Claude Code, Cursor and AI agents - Rust local-first AI memory with hybrid search, SQLite, knowledge graph and Python/TypeScript SDKs
Local-first temporal knowledge graph memory for AI agents. Runs with Ollama — no API keys required. Single Go binary + SQLite. Hybrid search, MCP server, REST API, interactive TUI.
Self-hosted shared context, memory, coordination, and evidence for Claude Code, Codex, Kiro, OpenCode, and MCP agents.
Governed local memory for AI agents: facts are retired, not overwritten, and every call is audited.
Immortal cellular AI tooling ecosystem built on Model Context Protocol (MCP) with dual-backbone orchestration, persistent knowledge graph, and multi-client profiles.
A compilation-free, lightweight Universal Agent Memory (UAM) system for Claude Code, OpenCode, Codex, and Antigravity.
An AI organism - the human-AI interface layer. A safety reflex that refuses known lethal actions even when the model is fooled, and a memory that only keeps what actually worked. For code, research, w
Rust MCP server with 35 tools for structured reasoning, self-improvement, semantic session memory, and agent/team coordination powered by the Anthropic Claude API
MCP server for RAG knowledge base search — local embeddings (fastembed/ONNX) + vector search (LanceDB)
Standalone MCP server giving AI assistants persistent, self-organizing memory over the SERAPH geometric knowledge engine (C ABI, no Python).
A local CLI that remembers failed commands and what fixed them, asks your coding agent why before it edits, and keeps you able to explain your own code.
Conversation knowledge extraction and reconciliation for multi-LLM development workflows
Cognitive digital twins and behavioral modeling for AI agents.
Your Ultimate Local AI Memory Hub 2026 – Eliminate AI Amnesia Today
Memory MCP server for persistent context storage and retrieval with PostgreSQL and pgvector.
Analytical memory for AI agents: a real Postgres queried in plain English over MCP. One command.
Graph-based retrieval for Obsidian vaults with Hebbian synaptic plasticity
Local context cache and code map for AI agents, written in Rust. 100% offline, zero dependencies. MCP server included.
Your coding agents forget between sessions. oboete remembers, on your machine: one Rust binary for Claude Code, Codex and Grok Build, with search, MCP tools and a local web page.
A context-first, deterministic, single-file database for AI agents — SQLite for AI memory. Records, typed graph relations, BYO embeddings, and time under one ACID transaction. No-LLM by contract: hybr
Open-source, LLM-agnostic second brain. Connect any LLM (local llama.cpp, Claude, Codex, GPT, Gemini, Grok, Ollama) via MCP — memory lives as Markdown in YOUR GitHub repo, independent of any model. De
Thalamus: a small governance layer over CortexDB for the shared knowledge of an organisation
Let your AI apps search your own files, privately. A Windows desktop app and MCP server with local hybrid (keyword + semantic) search over your folders. No cloud or API key needed.
High-performance Go tools for LLM Agents (MCP/CLI). 100x faster than Python. Includes native MCP Server, token-optimized search, and persistent project memory.
Open-source, self-hosted team memory for AI coding agents. Share, search, and audit project context through MCP.
Self-improving context & memory for Claude Code and OpenAI Codex. One canonical knowledge store injected only when relevant — hooks push budgeted context, an MCP server serves depth on demand, and it
Model Context Protocol Server with RAG knowledge base
My personal AI memory layer — vector store + session consolidation + MCP server wired to GitHub Copilot.
MemVault — The Shared Memory Layer for Every AI Agent You Run. Self-hosted, open-source MCP memory server with auto-injection, hybrid (BM25+vector) search, and zero-config sync — works with Codex, Cla
完整目錄
RAG、圖譜與代理長期記憶。共 2,653 個伺服器,最常用的排在前面。每個都會開啟發布者的頁面。