tool-use

DeepSeek-native AI coding agent for your terminal. Engineered around prefix-cache stability — leave it running.

✨ All your agents and workspaces in one place, on every device you own. Track tasks on a board, accessible from desktop, mobile, browser, or API. Self-hosted.

Awesome MCP Servers - A curated list of Model Context Protocol servers

A harness optimized to smaller LLMs

🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.

Apache Maka (Incubating) is a local-first AI agent workspace. Model messages, tool calls, tool results, permission decisions, and termination events are recorded as an append-only log.

Democratizing AI scientists with ToolUniverse

Open-source agent platform for Global × China enterprises — wire every system through one agent core. Self-hosted, any LLM.

ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning & ReCall: Learning to Reason with Tool Call for LLMs via Reinforcement Learning

Easily create LLM tools and agents using plain Bash/JavaScript/Python functions.

"AnyTool: Universal Tool-Use Layer for AI Agents"

ScienceClaw is a personal research assistant built with LangChain DeepAgents and AIO Sandbox infrastructure, adopting a completely new architecture beyond OpenClaw. It offers stronger security, better transparency, and a more user-friendly experience.

TypeScript AI agent framework: cognitive memory, runtime tool forging, multi-agent orchestration, 11 LLM providers.

Second Brain is an agentic framework that acts as an operating system, using local file intelligence, workflow automation, and LLMs to complete tasks and communicate over multiple modalities and messaging platforms.

kani (カニ) is a highly hackable microframework for tool-calling language models. (NLP-OSS @ EMNLP 2023)

[ICLR'25] BigCodeBench: Benchmarking Code Generation Towards AGI

MCPMark is a comprehensive, stress-testing MCP benchmark designed to evaluate model and agent capabilities in real-world MCP use.

Harness-oriented agent system framework for production-grade LLM agent applications

One agent. Every kind of work.

AutoHarness: Automated Harness Engineering for AI Agents