Context, Memory & RAG tools for MCP

Local-first AI memory system that stores conversation history verbatim and retrieves it with semantic search through a structured palace architecture (wings, rooms, drawers). Achieves 96.6% R@5 on LongMemEval with zero LLM calls, making it the best-benchmarked open-source memory layer for agents that need cross-session persistence without cloud dependencies

Agent memory system organized around three explicit operations—retain, recall, and reflect—with semantic, keyword, graph, and temporal retrieval plus an MCP server. The June 2026 release and production usage make it a concrete reference for turning cross-session persistence from passive storage into an active learning layer inside the harness

One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.

Persistent memory for AI coding agents delivered as a single Go binary with SQLite + FTS5 and 18 MCP tools for save, search, session lifecycle, and conflict detection. The agent-agnostic, zero-dependency design makes cross-session memory a local harness primitive rather than a managed cloud service

Code search primitive that replaces grep+read cycles with natural-language retrieval, cutting active tokens by ~98% while keeping 99% of a transformer-based retriever's accuracy. Ships as an MCP server and CLI, runs on CPU with zero external dependencies — the right drop-in for any coding agent harness struggling with context pressure

AST/tree-sitter code search MCP server that indexes a codebase and returns compact, relevant snippets to reduce coding-agent context usage

Typed graph database where agents branch and merge like Git. S3-native, Rust, traversal + vector + BM25 in one runtime

Self-improving executable context layer for data and analytics agents: it ingests warehouses, BI tools, and wikis to build a semantic layer with approved metrics, joinable columns, and resolved fan/chasm traps, then serves the result to Claude Code, Codex, and Cursor through MCP. Fills the gap where general-purpose agents invent metric logic on every question — it turns warehouse querying from a p

大模型（LLM）全栈学习路线与中文教程🔥：覆盖 Prompt Engineering、RAG、AI Agent、MCP、微调、模型部署、Transformer、AI 编程与大厂面试，从入门到生产实践。

Self-hosted persistent memory layer with an 8-stage consolidation pipeline (episodes → facts → relationships → patterns) and built-in MCP server. The critical gap it fills: production-grade cross-session memory without cloud dependencies or complex infrastructure — a single Docker Compose gives you Postgres, pgvector, and background consolidation

AI 应用开发、AI 编程实战与面试指南，涵盖 LLM、Agent、RAG、MCP、Claude Code、Codex 等核心技术与工程实践。

by David Corvoysier - Durable cross-agent memory for Claude Code, Codex, pi, and Hermes. Your memory is a Hugging Face dataset you own: recall it from any machine or share it with your team. Single binary, local index, pinned local embedding models

Governed shared memory for AI agent fleets, with multi-agent and multi-tenant support, MCP integration, trust tiers, audit trails, knowledge graph capabilities, and self-improving retrieval

Turn your workday into structured workflows agents can execute. 100% local, served over MCP.

Agent Systems Handbook by Prompthon — A practical AI agents handbook covering agent systems, agentic workflows, LangGraph, MCP/A2A, context engineering, agent memory, evaluation, observability, and multi-agent architecture. Current trend focus: Gemini Interactions API and managed agents, emerging agent runtimes, and production AI workflow patterns.

by plur-ai - Open, local-first engram memory for Claude Code. Engrams are plain-text YAML you can read, correct, and delete. The same memory is shared across MCP tools and multiple providers

Memory component for agents that keeps each memory with its source evidence in one local SQLite file and retires memories recorded as depending on a source when that source is corrected; TypeScript SDK, stdio MCP server, CLI and HTTP API, with exact replay and bisect in the 3.0 pre-release. MIT

CLI that benchmarks SDK, CLI, and MCP guidance docs (SKILL.md) against multiple LLMs and runs an iterative optimizer to rewrite them until every configured model meets a score floor

Local-first, full-text code search engine built for AI coding agents. Sub-100ms search across 10k+ files via trigram indexing, with structured JSON output and an optional MCP server so agents can query your entire codebase in a single tool call

by Wolfe-Jam - Authors and versions CLAUDE.md and AGENTS.md from a repository's actual detected stack, so Claude Code's project context stays in sync with the code instead of drifting. One typed source file (project.faf, an IANA-registered media type) is the single origin for every assistant's context file; a deterministic score reports how complete that context is. The file lives in the repo and

Bitemporal knowledge graph as agent memory

Code architecture visualizer: paste any GitHub/GitLab URL → interactive dependency graph (9 layouts, 16 colour modes), A–F health score, security scanner (SARIF 2.1 export), blast radius, churn heatmap, ORM query map, and AI chat (15 providers). 116 MCP tools with Kuzu graph DB + SQLite brain. Zero data collection, everything runs locally

P2P agent collaboration over XMTP with schema-based skill invocation, E2E encryption, and revocable trust. Agents share capabilities without exposing code

by jungjaehoon-lifegamez - Always-on companion for Claude that remembers your decisions and their evolution. Local-first memory using SQLite + transformers.js embeddings

by serpro69 - 🦫 Privacy-first virtualization layer for LLM context with MCP protocol for tool access

Open-source linter for AI context files (CLAUDE.md, .cursorrules, copilot-instructions.md) that catches stale paths, wrong commands, and token waste by validating against the real codebase

by sara-star-quant - Per-repo memory, outcome telemetry, and a calibrated-confidence gate for Claude Code, with MCP and AGENTS.md projections so other AI coding tools can read its context. Notes survive sessions; success claims need test evidence; your reverts are remembered. Local-only, stdlib runtime

CLI for managing Claude Code project configs across custom providers (Databricks, Bedrock, OpenRouter, LiteLLM, Cloudflare). Overlay merge/remove, MCP web search setup, multi-provider switching, team config export/import

CLI and MCP server that generates AGENTS.md/CLAUDE.md from static analysis of codebase structure, git history, and convention detection. Surfaces hub files, co-change coupling, and blast radius. No LLM required

Persistent multi-tenant memory layer and MCP server for AI coding assistants with sub-50ms hybrid recall

Apache-2.0 protocol for two agents, or an agent and a person in a browser, to settle typed terms: each side declares a schema, moves are validated against it, private limits stay with the relay, and agreement is both humans approving the SHA-256 of the same canonical terms. Spec, dependency-free TypeScript reference implementation, JSON Schemas and test vectors

Cross-agent registry and CLI for discovering and installing 220+ AI assets including skills, prompts, MCP configs, and workflows