Persistent memory and RAG for AI coding agents. Episodic memories with decay + durable concept graphs. MCP server + CLI. Rust.
Neuro-Symbolic Law-to-AST Compiler, Microsoft Z3 Formal Verifier, 12-MCP Suite, Contextual+Graph RAG, and Autonomous PR Enforcer (JusticeSphere AI / ComplianceOS)
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
MCP server for RAG knowledge base search — local embeddings (fastembed/ONNX) + vector search (LanceDB)
Read-only MCP server that lets Claude search and read your LogSeq graph: page context, link traversal and journals by date. Batched Datalog keeps a question to a handful of calls. Native Rust binary,
Self-improving long-term memory for AI agents in Rust. Safety-gated procedural learning, MCP server, Python/Node SDKs, and durable memory.
Local-first Code Knowledge Graph and MCP retrieval engine for AI coding agents. Built with Rust, SQLite, and Tree-sitter. No database server required.
Multi-provider LLM agent backend with RAG, Python toolpacks, SSE streaming and MCP server. Supports OpenAI, OpenRouter and Ollama with per-session routing, tool-calling loop and OpenTelemetry observab
Conversation knowledge extraction and reconciliation for multi-LLM development workflows
Your Ultimate Local AI Memory Hub 2026 – Eliminate AI Amnesia Today
What your agents know about your system: a 114-language code graph, memory and knowledge, in a local CLI and MCP server (33 MCP tools, 3 domains). Holds your data sources' structure, never their rows.
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
Self-growing procedural knowledge layer for AI agents. Rust MCP server + CLI — recall relevant knowledge before tasks, record outcomes after, distill experience into reusable insights. Works with Clau
Rust MCP server with 35 tools for structured reasoning, self-improvement, semantic session memory, and agent/team coordination powered by the Anthropic Claude API
My personal AI memory layer — vector store + session consolidation + MCP server wired to GitHub Copilot.
MCP server that builds a knowledge graph of a GitHub org's repositories, dependencies, languages, teams, and topics using FalkorDB
Analytical memory for AI agents: a real Postgres queried in plain English over MCP. One command.
CodeNinja Atoms: a sovereign AI operating system for the physical world. Open reference architectures for physical AI, with ontologies, model registers, costs and DOIs. CC BY 4.0.
Best Token-Efficient AI Coding Tools 2026 – Reduce Costs 90% with Local Memory & MCP
Apple ecosystem MCP server for Claude Code, Cursor, and other AI assistants — Notes, Reminders, Contacts with BERT semantic search
A simple Memory MCP server written in Rust
MCP (Model Context Protocol) Server for Retrieval Augmented Generation using Mongo and Gemini, OpenAI, with A2A support Grok
CogniMem is a local MCP server in Rust that gives coding agents a persistent cognitive memory layer.
Shared, encrypted, verifiable team memory for coding agents (MCP server)
Serveur MCP pour bases de connaissance markdown versionnées en git. Des sessions Claude isolées les lisent et y déposent des propositions ; seul le rôle gestionnaire intègre.
MCP server to allow agents to learn from my personal knowledge management system.
A high-performance Model Context Protocol (MCP) server written in Rust that extends AI models into autonomous coding agents with semantic memory, built-in Git tools, and codebase indexers
Parallax - an MCP server of independent correctives for a model's predictable failure modes: adversarial verification, deterministic checks (Z3/evalexpr), verified cross-session memory, cited research
Layered, self-learning knowledge base for teams, served over the Model Context Protocol. PostgreSQL + pgvector hybrid search, roles, audit log, YAML layer presets.
Cross-session persistent memory MCP server for AI assistants — local SQLite + FTS5, zero external dependencies
Persistent semantic memory service and MCP adapter for AI agents, powered by PostgreSQL and local Ollama models.
Rust MCP server for HaloPSA - ticket management, workflow actions, and semantic search via the Model Context Protocol
Stable MCP supervisor proxy for stdio servers: cached discovery, unified mcp.wrapper lifecycle control, and on-demand backend processes.
Local-first semantic-search MCP server over a personal CS/FP/graphics library
A minimal Rust vector-memory server that works with Qdrant and Ollama.
Model Context Protocol (MCP) server for FalkorDB — read-only graph access for AI assistants
Diretório completo
RAG, grafos e memória de agente de longo prazo. 2,653 servidores, os mais usados primeiro. Cada um abre a página do publicador.