Coding agents & developer tools
Autonomous coding agents
4,327 agents · most starred first
Autonomous coding agents, page 42 of 44
Minimal AI coding agent with multi-agent cluster — stripped, independent, research-grade
TopCode — next-generation CLI agent framework (State-Manifold paradigm)
Deterministic Agentic Governance Framework for Autonomous Software Engineering
An agentic coding terminal you can also drive from a web page.
Agentic AI vibe coding CLI with free model support
Platform Agentic AI CLI Global with 9router integration, SQLite Second Brain, and Reasoning Mitigation Engine
Turns a plain notes repo into a bridge: one repo that holds the plan and drives agentic work across your other repos.
Holmes-Kit — deterministic Agentic Software Engineering (ASE) harness with causal traceability (spec chain + D-CPG + RTM + phase guardrail)
Agentic AI environment built on the Pi coding agent harness
Terminal-native node-graph interface for running and observing agentic coding workflows
Install and run Aether Agent, the open-source terminal coding agent, from pip or pipx.
In-guest Agent Protocol server that drives the Claude Agent SDK for Athena coding tasks
A CLI coding agent with full observability, multi-model support, and security guardrails
Claude.ai RE Client v4 — CLI client, session manager, and autonomous coding agent.
The reference software engineering harness and runtime for autonomous coding agents.
Run coding agents on Fountain, with real computers, repositories, and credentials.
Hamster: a lightweight CLI software engineering agent powered by OpenRouter.
一个基于 Textual 的终端 TUI 编码 agent
Browse and resume local coding-agent sessions
An open-source local coding assistant powered by Ollama.
Permissioned coding-agent CLI with durable planning and isolated execution.
A lightweight, hackable mini-OpenCode written in Python.
TARS — a disciplined, multi-session coding agent loop
A terminal coding agent
The open-source compiler and multi-agent runtime for coding agents
TokenKoding Code — agentic coding CLI. Talks only to api.tokenkoding.id.
Verification-first agentic bug fixing system
Weaver — Coding agent dệt plan, code và test thành phần mềm chạy được. Xây dựng với LangGraph: Planner → Analyzer → Coder → Tester → Reviewer, tự sửa khi test fail.
A framework for running AI agent workflows against code repositories.
BitFun CLI - terminal AI agent
Local cockpit for running and tracking AI agent tasks in your repo. Uses your logged-in `claude` CLI and `gh` — zero config, zero database.
Autonomous terminal coding agent with multi-critic loop engine (Bun-native TS).
Cross-agent, human-governed software delivery harness
Governed autonomous variation runtime: evidence-driven repository engineering loops with bounded authority, replayable receipts, semantic supervision and RVF working memory.
AI CLI for software engineering — chat with OpenAI, Anthropic, Google, Groq, Together AI and custom endpoints
DeepSeek coding CLI — planner/worker/reviewer agentic loop
TjAgentForge CLI Agent — local executor that proxies your local git repos (branch / apply patch / commit / push) with source code never leaving your machine.
Gemini Code Assist review: compare features, pricing, use cases, access model, and alternatives for this Coding Assistant agent in 2026. Gemini Code Assist is an AI-powered coding assistant for software development.
Explyt AI Agent: a terminal AI coding agent
AI Agent Workflow Coordinator — kanban-based pipeline for AI coding agents
Alias for @wjarka/cezarion — so `npx cezarion` just works. Local cockpit for running and tracking AI agent tasks in your repo.
A terminal-based AI coding assistant. CodeYantram brings an LLM agent into your terminal — chat with the model, and let it read, search, edit, and execute against your project — all with full streaming, a built-in approval gate for anything that mutates,
Ultra-lightweight, scalable CLI/TUI coding agent optimized for tiny local models & remote runtimes
Klyro — autonomous coding harness CLI that streams from any OpenAI-compatible or Anthropic LLM endpoint.
A minimal coding agent CLI built to learn agent harness architecture.
Interactive coding agent (Pi) with UiPath LLM Gateway and BYO provider support.
Navarch machine-side session manager: claims delivery tasks and runs them through local coding agents.
KajiCode — a fast, multi-provider terminal coding agent.
A coding-agent CLI that works the same way whether the model is Claude, GPT, or an open-weight model like Qwen, DeepSeek, GLM, or Llama running locally.
hncode — A cyan-blue TUI AI coding agent with zero runtime dependencies.
gu: the coding agent in your terminal. It reads your repo, makes the change and runs the tests, with your own models (Ollama or any OpenAI-compatible provider). Free installs keep the agent, its API and its database on your machine. macOS, Linux and Windo
Felan Code: an open-source, model-portable coding agent built for cost-efficient, verifiable software work
Every provider. One terminal. Agentic coding CLI with MCP, skills and plugins.
Nexora — One Agent. Any Model. Any Workspace. (Terminal CLI)
Autonomous terminal agent harness engineered to understand software tasks, conduct web research, reflect on tool plans, safely modify codebases with automated verification, execute commands in Docker, enforce safety guardrails with secret scanning, and re
/ship takes one sentence to verified code. Terminal coding agent for DeepSeek and any OpenAI-compatible endpoint. Zero-dependency launcher for the DeepSeek Harness.
AI coding CLI powered by OpenRouter - Free and open source
Overarch v2.0.0: Autonomous AI Software Engineering Platform, D-HFR Mesh, Full-Screen Dark TUI, and Universal Harness
Terminal-native autonomous AI coding agent with client-side tool execution and DLP guardrails
Repo-issue–driven autopilot runner
Autonomous multi-agent migration and refactoring engine powered by Mozaik v4
Remote multi-agent development workspace for the official Claude Code and Codex CLIs
Olives Technologies Engineering OS — Autonomous Multi-Agent AI Engineering Environment
Durable multi-agent coding runtime for Pi, Claude Code, Codex, and Specialists
TUI-first, document-driven multi-agent coding runtime
Auton CLI agent - plan→act→verify→repair loop with multi-agent worktrees
Bun-native coding agent with OpenTUI, persistent sessions, policy-controlled tools, MCP, and live multi-agent orchestration.
Laila: An advanced, local-first AI developer assistant with MCP, Vision, and Multi-Agent Swarm capabilities.
A maximalist, model-agnostic coding harness for the terminal, with lazy skills, tools, MCP and multi-agent orchestration.
radical-code — Rust AI development framework CLI: setup wizard (config.db + encrypted secrets vault), TUI, REPL, multi-agent dispatch, MCP brain.
Guided feat/bug workflows (start→ship), post-deploy monitoring and multi-agent code review, stack-agnostic. Each repo uses a shared FLOW.md plus optional harness overlay.
A model-agnostic terminal coding harness with multi-agent collaboration
Reusable Ralph workflow pattern - ticket-driven development with multi-agent review loops
Agentic coding assistant
makecli — agentic development platform cli
Agent orchestration patterns over long-running coding agents
Run several coding agents in isolated worktrees with shared coordination.
A reproducible algorithm optimization agent for C++ and Python
One API over the coding agents installed on a machine: Claude Code, Codex, Cursor, and more.
Anzar — Local-first AI Software Engineer Agent
One headless turn of a coding agent (Claude Code or Codex) through the vendor SDKs: explicit knobs, a deadline that kills the tree, one result.
Codebuff JupyterLab Extension - Thin client for Agent Server
FluxImp Agent: an AI agent harness for coding and web research
Turn a project idea into a structured plan and a starter repo that provably builds
A governed, cross-platform SDLC toolkit for AI coding agents.
Embed the kiss coding agent in a Python program
Evidence-backed dependency migration assistant (experimental alpha)
终端里的编码 Agent:配置驱动,支持 OpenAI Chat / Responses 与 Anthropic 协议、MCP、Agent Skills
A minimalist coding agent
A terminal coding agent with tool calling, context management, subagents, MCP, and skills.
A coding agent with zero runtime dependencies. Stdlib-only Python.
A small, local, message-driven coding agent.
A terminal coding agent, built from scratch in layers.
one — autonomous terminal agent (CLI + TUI + JSON-RPC); optional human cooperation mode
Persistent Python, long-lived sub-agents and a continual harness for the coding agent you already use
Otto: a terminal AI agent built around measured results -- one agent loop, a rubric-first evaluator, tiered memory, multi-vendor routing, and six benchmark harnesses.
编码 agent 框架:单 agent core + 扩展(MCP / 多 agent / web)
Self-contained Spec Circuit Requirements Agent (CLI + Textual TUI)
Autonomous terminal-based coding agent designed around verifiable software changes. Build. Verify. Ship.
Tinet Agent CLI Orchestrator