Local-first Memory Wiki for AI agents
Self-hosted LLM wiki turning project context into OKF memory
ENGRAM — an epistemic memory substrate for AI agents. Public release snapshots (one squashed commit per version).
RAG pipeline for documents (Markdown, PDF, images). 10-step hybrid search, LLM enrichment, taxonomy, MCP server. Cloud or local.
Shared code intelligence for agent fleets — AST-aware semantic search + multi-agent memory with git-concurrent coordination
Local-first, self-hosted lifelog app for recording, searching, and analyzing your life with AI through MCP.
MCP server for RedM / RDR3: native lookups (hash name), semantic search, VORP, RSGCore, oxmysql, rdr3_discoveries community data. Hosted HTTP endpoint, no auth.
Agent-native incident investigation graph: analysts and AI agents (MCP/REST) link evidence from EDR, Entra ID, cloud and GitHub logs into one shared, real-time attack graph and timeline. Self-hosted,
Automate application assembly using semantic search for smart library selection on the Machanism platform.
A tool for retrieving Discord messages and storing them in a vector database for semantic search and analysis.
Shared memory MCP server for multi-agent projects. Agents (Claude, Cursor, Codex, AntiGravity) write to a local `.agent-mem/` folder so the next agent picks up where the last one died.
Self-organizing retrieval fabric for AI memory — deployable MCP server, REST API, and Python SDK
The WireCat desktop app: search your chats, meetings and notes, connect any AI agent to them, and approve what it remembers. Local-first, for macOS, Windows and Linux.
API service to search vectorized Cursor IDE chat history using LanceDB and Ollama
Local RAG MCP server with hybrid search, PDF/DOCX support, and zero-config setup
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.
A fast, cross-platform build system and task orchestrator for polyglot monorepos. One statically linked Go binary, no second toolchain to install.
All-in-one open-source toolkit for reliable AI agents: memory, code search, safe execution, and evaluation in one npx install.
Agent-first adaptive learning platform. Create courses as YAML knowledge graphs via CLI or MCP server. AI agents scaffold, fill, review, and publish — no UI required. Adaptive diagnostics, spaced repe
Code intelligence MCP server for AI coding agents. AST-level codebase understanding — semantic search, symbol navigation, real reference graphs, and cross-language bridge detection across many languag
NotDory is durable memory your agents manage themselves — so every session starts where the last left off.
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
Persistent AI memory server with hybrid semantic search (MCP protocol)
A self-hosted MCP server (Go) that reduces AI context window usage by sandboxing large tool outputs and returning compact summaries instead of raw text.
Zero Trust for Agentic AI. Secure Every Tool Boundary. Control which AI agents can use which tools
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
MCPBlade is a powerful aggregation and management service for Model Control Protocol (MCP) servers. It provides intelligent tool discovery, semantic search, and smart routing capabilities to seamlessl
Governed local memory for AI agents: facts are retired, not overwritten, and every call is audited.
MCP server for Eruka — anti-hallucination context memory for AI agents
A Model Context Protocoll (MCP) server that validates content against official MCP specification using semantic search and AI-powered validation.
Graceful degradation for concurrent LLM/agent terminals: cheap /proc-signature load-shedding, a shared crash-safe ledger, and legible post-mortems. Fail legibly, not catastrophically.
Self-hosted Obsidian-compatible markdown vault with a first-class MCP server for AI agents.
Persistent, citable memory for any AI agent: verbatim markdown vault, temporal knowledge graph and local hybrid search over MCP. R@5 0.981 on LongMemEval-S with 0 LLM calls.
MCP server wrapping semantic-memory — local-first knowledge management with evidence-scored retrieval, contradiction detection, and adaptive routing
Basic Memory MCP server integration, for Zed Editor's Assistant.
Comprehensive memory management system for LLM agents implementing episodic, semantic. Built in Rust with MCP server support for Kiro CLI
Gesamtes Verzeichnis
RAG, Graphen und Langzeitgedächtnis für Agenten. 2,590 Server, die meistgenutzten zuerst. Jeder öffnet die Seite des Herausgebers.
