code-agent

Practical productivity tools for Claude Code, Codex-CLI, and similar CLI coding agents.

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.

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

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

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.

Official implementation of Controlled Self-Evolution for Algorithmic Code Optimization

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.

Source code for the Build Your Own Coding Agent book

Advances and Frontiers of LLM-based Issue Resolution in Software Engineering A Comprehensive Survey

Automated loop driver, slash commands, council automation, MCP browser bridge, and portfolio governance for Claude Code CLI

CoDA-Bench is a benchmark for code agents on data-intensive tasks. 🎈代码智能体能搞定数据密集型任务吗?

Evaluate (lint, review, and security-audit) your AI coding agent harness.

Trace Claude Code AI coding assistant conversations, user inputs, and tool usage with Langfuse for comprehensive observability.

CodexOpt: Optize your Agents.MD and Skills for Codex with GEPA

Build coherent and visually polished multimodal webpages with hierarchical planning, AIGC tools, and iterative reflection.

Agentic Code Optimization For Better Coding Agent Experience

AgentPrecept — Agent 的方法论文档治理工具。project-graph 让 Agent 快速定位模块关系，L4_O01 记录每次决策，HANDOFF 确保换班不丢进度。三层门禁：Agent 自助检查 → 本地 hook → CI 兜底。设计门禁验证文档存在（不校验质量）。涟漪分析覆盖显式依赖，不支持动态反射和微服务调用。不是安全扫描器，不是万能银弹——只是一份诚实的施工图。

deepseek code agent for web client

RAT: RunAnyThing via Fully Automated Environment Configuration (EMNLP 2026)

Search-Enhanced Interface for Multi-Expertise Integration (SEIMEI): Realtime-Knowledge-Update AI System with Intelligent Search