Agents for deep research, retrieval, knowledge work and scientific workflows. Every project is open source and ranked from public GitHub adoption, maintenance, quality, relevance and demand evidence.
Coverage changes as the GitHub scanner discovers and re-evaluates projects. Rankings are discovery signals, not paid placement or hands-on product reviews.
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
Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience
The agent engineering platform.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.
18 Lessons to Get Started Building AI Agents
Caura (formerly MemClaw) — governed shared memory for AI agent fleets. Multi-agent, multi-tenant, MCP-native. Trust tiers, keystone policies, audit trails, knowledge graph, self-improving retrieval. Apache 2.0.
Framework-aware code intelligence MCP server for Claude Code and Codex — 70.5% fewer input tokens to review a pull request, median over 60 merged PRs in repos we don't own. 81 languages, 87 frameworks, 100% local.
Open a project to inspect its evidence, or use Opportunity Radar to turn recurring GitHub requests into a guided validation sprint.
Explore demand signals