RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
Auditable context engineering for AI agents: context optimization, recoverable context compression, receipts, answer verification, and MCP for Claude Code, Codex, OpenClaw.
Structured planning and persistent context for AI coding agents. Plan multi-phase work once and any agent (Claude Code, Codex, OpenCode) executes it across sessions without losing the thread.
🧠 Local-first LLM state branching & debugging. Capture, visualize, branch, and regression-test LLM calls as a DAG. Free & local via Ollama, any OpenAI-compatible API, MCP for agents. Zero config.
天枢 (Tianshu) 是一个基于harness工程的终端编程智能体运行时(Tui X Gui),针对DeepSeek V4 做了前缀缓存工程优化(长会话实测稳态命中率 97–99%)和深度适配。它跳出了传统 AI 编程助手把大模型仅当成“工具”的局限,基于认知虚拟机 (CVM)、自感知层和信息素(Stigmergy)自衰减记忆构建,让 AI 成为有独立判断与认知防护的“开发伙伴”。
Enhanced fork of OpenWolf — a token-conscious second brain for Claude Code, with bounded storage, self-maintenance (openwolf doctor), .wolfignore scoping, and tunable retention. AGPL-3.0.
CASP — the Coding-Agent State Protocol. A 200-line discipline for AI-coding sessions.** Machine-verifiable session state + drift validator + canonical templates. Works with Claude Code, Cursor, or anything that drives a repo with a session loop. Built by Thales (Juste Gnimavo) (https://thalesandhisaictoclaude.com)
Your agent forgets; nem doesn't. mnemonics encodes a session's decisions, edge-cases and facts into immutable, recallable structure — versioning agent context the way git versions code, shared across Claude & Codex.
Agent Session Manager - A comprehensive Elixir library for managing AI agent sessions, state persistence, conversation context, and multi-agent orchestration workflows