Self-hostable, git-native knowledge base & AI memory (MCP) — your notes stay plain Markdown files in your own git repo. Pure-stdlib Python, no database. AGPL-3.0.
Persistent semantic memory for AI. An MCP server that turns every conversation into a living concept graph — vector search, Hebbian link reinforcement, spreading activation — so your LLM remembers acr
Local-first cross-corpus retrieval MCP server — model2vec embeddings + LanceDB (Tantivy BM25) + SQLite. One binary; hybrid (dense + BM25) search across markdown, code, and Claude Code sessions.
Go SDK, CLI and MCP server for streaming agents, tools, memory, retrieval and evaluations, with pluggable model providers and durable execution.
Source-backed local memory shared by Claude Code, Codex, pi, and MCP clients. No generative LLM.
Self-hosted, self-learning, provider-agnostic personal agent kernel. Local-first memory in one SQLite database, project-scoped, reachable from any tool over MCP or a CLI.
A memory of the codebase your AI agent can't get from grep: a persistent call graph, semantic search, and per-symbol review learnings over any repo. Self-hosted MCP server — Go, tree-sitter, Apache AG
Curated Roblox knowledge that improves Claude's work on Roblox scripting, VFX, UI and more, for everyone who installs it. Tip sharing is on by default and easy to turn off.
Unified Workspace with Multi Agent memory - Slipstream - 5-layer associative graph memory (MAGMA) with autonomous REM cycle, CLI, GUI, DXT-MCP Cloak Tools.
Local-first long-term memory for AI agents - plain Markdown vault + thin MCP server. CJK-aware BM25, token-efficient by design.
Local-first persistent memory MCP server for Claude Code, Codex, Cursor, Qwen Code, and AI coding agents. Cross-session, cross-agent SQLite memory.
Unified Memory Forensics MCP Server - Multi-tier engine combining Rust speed with Vol3 coverage.
Next Generation MCP service to query the NSF Open Knowledge Network Knowledge Graphs
IssueOps agent harness: team memory for coding agents. Cautions and ADRs ship in the same PR as the code. Works with Codex, Claude Code, Omo, omp, and opencode.
One memory for every coding agent you switch between: Claude Code, Copilot, Codex, Cursor, Antigravity. Markdown + git, MCP server
Persistent shared memory and coordination MCP server for multi-agent AI workflows. The memory component of the Junto system. MongoDB + ChromaDB. Production-tested with 6+ agents over 500+ sessions.
High-performance, SIMD-accelerated vector search engine and MCP server for .NET 10. Optimized for LLM embeddings and semantic search.
MCP server that gives AI agents fast, searchable access to the pgsql-hackers mailing list and PostgreSQL source code (threads, patches, authors, commits and a knowledge graph) to answer Postgres histo
A private, local memory layer MCP server for your LLMs
Local code intelligence graph for AI coding agents: Tree-sitter static analysis, structural code search, dependency impact, blast-radius analysis, CLI and MCP server.
Chat with your Obsidian notes, build research maps and review proposed edits using your chosen model connection.
MCP server for persistent memory. grug remember thing so not forget.
Autonomous M2M MCP server that scrubs framework noise & redacts secrets from AI agent error logs before they hit your context window
An MCP server implementation for retrieving information from the AWS Knowledge Base using the Bed...
Self-hosted git-native knowledge base with an MCP endpoint your AI reads, writes and rewinds
Cross-framework MCP server and CLI for MITRE ATT&CK, D3FEND, ATLAS and F3, with provenance on every link. Renders D3FEND CAD, Attack Flow, Navigator and Mermaid diagrams.
Shared long-term memory as a knowledge-graph MCP server — persistent context, preferences and project knowledge for Claude Code, opencode and any MCP-capable AI agent.
Persistent memory for AI agents — local JSON, zero config, no server required.
Memory MCP server for the Zed editor
The memory is yours. The model is a guest. Local-first memory and retrieval layer for AI agents: RAG with no model in the path, abstention as a verdict, MCP server, evaluation included. Rust, Apache 2
MCP server for agent memory over HexxlaDB—ring retrieval, embeddings + lexical search, seams, facets, YAML persistence policy, localhost HTTP transport.
MCP (Model Context Protocol) server for semantic code search. Replace grep/ripgrep with understanding-based code search.
Native macOS SwiftUI, Metal & VideoToolbox app for up to 120 FPS Android mirroring — HEVC/H.264 streaming, QR/Hotspot/BT bypass, Continuity, Vision OCR, SQLite FTS5 Recall & built-in MCP server.
HPC aggregation pipeline and API/MCP server for LLM-mediated biomedical data integration
HALO (Harness for Always-On Loop Oversight), from the survey Always-On Personal Intelligence: an evaluation harness and MCP plugin for always-on personal AI assistants and LLM agents. It checks whethe
Short-term memory proxy gateway with proactive memory surfacing for AI agents
Direktori lengkap
RAG, graf, dan memori jangka panjang agen. 2,619 server, yang paling banyak dipakai lebih dulu. Masing-masing membuka halaman penerbit.