A curated list of products, benchmarks, and research papers on autonomous code agents. Beyond coding — they're redefining how software changes the world.
-
Updated
Jun 7, 2026 - Python
A curated list of products, benchmarks, and research papers on autonomous code agents. Beyond coding — they're redefining how software changes the world.
Code Agent++ 面向 AI 编程 Agent 的外挂式增强与可靠性工程层。 Code Agent++ 不做另一个代码生成 Agent,也不替代 Codex、OpenCode、Claude Code、Cursor、MiMoCode 写代码。它的定位是 Code Agent Enhancement Layer:围绕 Code Agent 在真实工程中的常见问题,提供上下文、边界、验证、回归防护、幻觉抑制、影响分析和修复闭环等外挂式增强能力。
A toolkit that makes Claude Code better at engineering — session memory, dependency analysis, large file navigation, 18 specialist agents, and crew teams for parallel multi-branch work.
StepShield: A Temporal Benchmark for Step-Level Rogue Action Detection in Autonomous Code Agents
[ICML 2026] JustAsk: Curious Code Agents Reveal System Prompts in Frontier LLMs | Verified on Claude Code | Autoresearch for System Prompt Extraction
Governed local runtime for AI coding agents: task lifecycle, mandatory gates, reviews, doc-impact checks, and auditable completion.
Agent skill for generating professional PowerPoint decks. 7 composable skills and a purpose-built CLI.
No hype. No empty buzzwords. Just the map that matters
A service-boundary-aware document exchange center for coordinating heterogeneous LLM code agents via MCP. Implements versioned Markdown store, pub-sub notifications, and diff-aware update protocol.
Abundio is a GPU-accelerated, project-centric terminal workspace for AI-assisted development. Run your shells, coding agents, editor, git, and notes side by side — without leaving your project.
Deterministic method-first retrieval for AI coding agents.
Multi-channel notification platform for code agents — Telegram, Email, Web Terminal. Connect Kiro, Codex, Claude, Gemini with your messaging channels.
TDD coding agent
Provide ready-to-use AI agent personas for Claude Code to deliver expert-level output with minimal setup and clear specialization.
AI-first social media trend — built, managed, and extended through Claude Code.
Git hunk sifter for code agents — selective staging tool (git add -p replacement) for Claude Code, Codex, and similar CLI agents
Self-growing harness layer for Claude Code & Codex — pick the right harness per task, keep run state visible, and watch toolkit health on a local 3D dashboard.
Free no-signup Claude Code settings.json hooks checker and browser-only validator.
Apply unified diffs and fuzzy search/replace edits in pure Python - the patch engine for code agents. No git, no patch binary.
Portable, validated patch packages for Git working trees.
Add a description, image, and links to the code-agents topic page so that developers can more easily learn about it.
To associate your repository with the code-agents topic, visit your repo's landing page and select "manage topics."