GeezerVison

RepoMaster: The open-source AI agent that masters GitHub. It turns any code repository into a powerful tool, achieving a new level of autonomous task-solving. An open alternative to Claude-Code.

swe-agent claude-code openhands code-agent mle-bench gittaskbench

Updated Nov 5, 2025
Python

Blushyes / coro-code

Star 370

Open-source CLI coding agent, a free alternative to Claude Code. Generate, debug, and manage code seamlessly.

agent cli llm gemini-cli claude-code code-agent cli-agent

Updated Oct 30, 2025
Rust

SE-Agent is a self-evolution framework for LLM Code agents. It enables trajectory-level evolution to exchange information across reasoning paths via Revision, Recombination, and Refinement, expanding the search space and escaping local optima. On SWE-bench Verified, it achieves SOTA performance

mcts code-fix swe-agent test-time-scaling claude-code code-agent swe-bench self-evolve

Updated Sep 23, 2025
Python

RUC-NLPIR / FinSight

Star 278

[ACL 2026 Main, SAC Highlight] FinSight: Towards Real-World Financial Deep Research. 🎯One ticker, one click, one publication-ready report.

agent financial financial-analysis multi-agent-system rag llm finance-ai deepresearch code-agent

Updated Apr 6, 2026
Jupyter Notebook

QuantaAlpha / GitTaskBench

Star 261

Repo-level benchmark for real-world Code Agents: from repo understanding → env setup → incremental dev/bug-fixing → task delivery, with cost-aware α metric.

repo-level swe-agent code-llm claude-code openhands code-agent repomaster

Updated Sep 22, 2025
Python

Staks-sor / ai-free

Star 228

Open-source local AI client and coding agent for DeepSeek, Qwen, ChatGPT and EconomyOS with memory, voice, browser tools, OpenAI/Anthropic-compatible APIs and VS Code.

cli ai memory developer-tools vscode-extension web-automation virtuals voice-input openai-api ai-agent chatgpt local-ai free-ai qwen deepseek openai-compatible-api anthropic-api ai-coding-assistant code-agent economyos

Updated Aug 20, 2026
JavaScript

dadiaomengmeimei / claude-code-sourcemap-learning-notebook

Star 168

Reverse-engineering Claude Code's 512K+ lines of TypeScript — architecture, design decisions, and 11 transferable patterns for building AI Agents

code-agent

Updated Apr 2, 2026

hwfengcs / DM-Code-Agent

Star 152

Local-first, auditable Python code agent. Ships its own 30-task hidden-test benchmark plus SWE-bench Verified scored by the official harness -- every number reproducible, negative results included.

agent mcp rag llm llm-agent react-agent agent-skills agent-evaluation reflexion-agent code-agent swe-bench

Updated Aug 27, 2026
Python

QuantaAlpha / EvoControl

Star 135

Official implementation of Controlled Self-Evolution for Algorithmic Code Optimization

code-efficiency code-agent self-evolution alphaevolve

Updated Jan 25, 2026
Python

oripress / AlgoTune

Star 119

AlgoTune is a NeurIPS 2025 benchmark made up of 154 math, physics, and computer science problems. The goal is write code that solves each problem, and is faster than existing implementations.

code-generation code-optimization llm-agent llm-coder llm-benchmarking code-agent

Updated Jun 24, 2026
Python

whut09 / opencode-plusplus

Star 113

OpenCode++: a Coding Agent Reliability Harness for OpenCode, adding context, edit boundaries, command evidence, verification gates, impact analysis, and repair loops.OpenCode++：面向 OpenCode 的 AI 编程可靠性增强框架，为其增加上下文管理、编辑边界、命令证据、验证门禁、影响分析与修复闭环能力。