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
-
Updated
Sep 8, 2026 - Go
An AI agent is a software system that autonomously perceives its environment, makes decisions, and takes actions to achieve goals — typically powered by large language models (LLMs). Unlike simple chatbots, AI agents can use tools, access external data, execute code, browse the web, and manage multi-step workflows without continuous human guidance.
AI agents range from coding assistants that edit files and run tests (Claude Code, Gemini CLI, Cursor) to browser automation systems (browser-use), computer-use agents (CUA), workflow builders (Activepieces), and multi-agent teams (CrewAI, deer-flow). The ecosystem includes memory layers (mem0), frontend toolkits (CopilotKit), sandboxed execution environments (E2B, Daytona), and full productivity platforms (Cherry Studio, LobeHub).
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
A disposable copy of your production stack for every pull request: masked Postgres, contained third-party APIs, and agents that use your app like people.
AI agent orchestration for open and closed source — a fully customizable fleet of AI agents covering every level of project maintenance, from brainstorming to full autonomy
Publish static HTML pages and get secure shareable URLs
Go SDK for declarative, stateless-per-step automation against task-tracking systems. A flow is an ordinary Go binary; each invocation advances one tracked item. Pluggable backends, GitHub Issues out of the box.
Agentic Runtime
Self-hosted project context for people and AI agents: specifications, repository knowledge, execution choices, and run evidence in one inspectable history.
Stonewall is a local sandbox for AI coding agents, drastically limiting access to tools, paths and project files, based on strictly enforced policies.
A Go SDK for LLMs: one typed API over the Anthropic, OpenAI and Gemini protocols, and an agent runtime that runs the loop around it
Personal compute fabric: schedule AI agent work and jobs across machines you own. The brain stays home.
AgentWorks: the open-source control plane for running, measuring, and improving AI agent workflows across your company.
Evidence-gated orchestration for coding agents: frozen tasks, independent verification, digest-bound review, draft-only publication. 证据门禁式 Coding Agent 编排器。
Sandboxed version control for autonomous coding agents: an agent's untrusted code runs in a per-task microVM, its work stays in an isolated, append-only store, and only the reviewed result lands in your git.
A Go REST API scaffold. chi, pgx + sqlc, OpenAPI codegen, OpenTelemetry, JWKS auth, migrations, and a generator for new resources.
ChatCLI is a command-line application that utilizes LLMs—such as those from Anthropic, OpenAI, and others—to facilitate interactive conversations within the terminal. At its core, it features a specialized agent and tools that provide unique expertise.
Yosuri — LESS CHAT, MORE AUTOMATIC. A 24H self-evolving AI agent that aggregates free models into one OpenAI & Anthropic-compatible API, picks its own tasks, writes real code, and verifies results. Local-first, free forever. AGPL-3.0.
Secure, policy-controlled development environments for AI agents, powered by pluggable isolation backends such as Incus.