agentic

bytedance/deer-flow

DeerFlow 2.0: a ground-up rewrite of ByteDance's super agent harness — DeerFlow 2.0 is a complete rewrite orchestrating sub-agents, memory, sandboxes and extensible skills to handle long tasks from minutes to hours. It recently hit #1 on GitHub Trending. Useful for developers building agentic research, coding, and content-creation workflows with LangGraph/LangChain.

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.

pingcap/tidb

TiDB positions its distributed SQL database for unpredictable agentic workloads — TiDB is a MySQL-compatible, distributed SQL database combining ACID transactions, HTAP analytics and vector search in one engine. It scales horizontally without downtime and avoids data silos or noisy-neighbor issues, aimed at teams building AI agents that need memory, context and unpredictable scale.

TiDB is built for agentic workloads that grow unpredictably, with ACID guarantees and native support for transactions, analytics, and vector search. No data silos. No noisy neighbors. No infrastructure ceiling.

Tencent/WeKnora

Tencent's Go-based platform turns documents into RAG, agents and wikis — WeKnora is a Tencent open-source framework that converts raw documents into a queryable knowledge base, combining RAG retrieval, an autonomous reasoning agent, and a self-updating wiki. It ships with Chrome extension and WeChat Dialog integrations, aimed at teams building Q&A chatbots and internal knowledge tools.

Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.

zeroclaw-labs/zeroclaw

A self-hosted Rust runtime for owning your AI agent end to end — ZeroClaw is a single Rust binary that runs a personal AI agent on your own machine, connecting to ~20 LLM providers and 30+ channels like Discord, Telegram, Matrix and email. It targets people who want full control over their agent, data and host rather than relying on a hosted service.

Fast, small, and fully autonomous AI personal assistant infrastructure, any OS, any platform — deploy anywhere, swap anything 🦀

strands-agents/harness-sdk

An open-source SDK for building and controlling AI agent harnesses — Strands Agents' harness-sdk lets you build an agent harness in Python or TypeScript and control it end-to-end, model- and cloud-agnostic. It ships as separate Python/TypeScript harness packages plus a CLI, aimed at developers building production agents rather than quick demos.

Build an agent harness and control it end-to-end. Open-source SDK for production AI agents in Python & TypeScript - any model, any cloud.

GCWing/OpenBitFun

An open-source agent workspace with four work modes and cross-device control — OpenBitFun 1.0.0 pairs a Rust agent runtime with a desktop app, offering four Agent Harness modes (Minimal, Standard, Ultimate, Creative) for tasks from quick fixes to multi-agent projects. It adds cross-device remote control and Mini App customization, aimed at users wanting a flexible, general-purpose agent beyond coding.

OpenBitFun combines a high-performance agent runtime written in Rust with a polished desktop application. It pairs the depth of a Code Agent with open, general-purpose capabilities for work beyond software development.

slavakurilyak/awesome-ai-agents

A curated, heavily categorized map of the agentic AI landscape — This list curates 300+ agentic AI projects across categories like agents, frameworks and tools, with each entry noting original submitters and current maintainers where known. Useful for developers scouting the fast-moving AI agent ecosystem for credible, actively maintained projects rather than abandoned repos.

Awesome list of 300+ agentic AI resources

croffasia/itsaplan

Self-hosted project tracker built for humans and AI agents together — A self-hosted alternative to Linear, Jira, Trello and Plane where AI agents act as teammates, not bolt-ons. Everything—boards, issues, sprints—is exposed via REST API, webhooks, and MCP, letting agents plan and ship work alongside people. Aimed at teams wanting agentic workflows in their issue tracker without vendor lock-in.

⭐️⭐️⭐️ Open-source, self-hosted alternative to Linear and Plane. Project management and issue tracking where teams and AI agents work side by side to plan and ship products.

SemiAnalysisAI/InferenceX

A standardized benchmark suite for GPU inference stacks — InferenceX from SemiAnalysis bundles end-to-end serving, networking/collective, and kernel-level benchmarks across vLLM, SGLang, and TensorRT-LLM on NVIDIA and AMD GPUs. It targets researchers and MLOps teams comparing inference hardware and software, with results published on a public performance dashboard and new agentic long-context benchmarks like AgentX.

Open Source AI Accelerator Research Platform Standard / 开源推理研究平台

openai/tunnel-client

OpenAI's own client for tunneling private MCP servers to ChatGPT — A Go CLI and SDK from OpenAI that lets private or localhost MCP servers reach ChatGPT, Codex, the Responses API, and AgentKit via a hosted tunnel endpoint, with no inbound firewall rules needed. Useful for teams blocked by security policy from exposing MCP servers publicly, with built-in healthz/readyz/metrics/ui for operators.

Customer-run client for Secure MCP Tunnel: connect private or localhost MCP servers to ChatGPT, Codex, the Responses API, and AgentKit without exposing them to the public internet.

acryldev/acryl

ACRYL - Agent Context Relay Yielding Lifecycles. One persistent workspace, one canonical context, any coding agent.