Results for “coding agent” — 237

Local-first resilient terminal coding agent with MCP client support ☆30

Shell and coding agent on mcp clients ☆673

Open-source desktop orchestrator for autonomous coding-agent teams with task delegation, inter-agent messaging, Kanban, and code review across multiple agent runtimes. !GitHub Repo stars

🐍 🏠 🎵 🎥 - A coding agent for Max (Max/MSP/Jitter), which is a visual programming language for music and multimedia.

The AI coding agent built for the terminal. !GitHub Repo stars

Local-first CLI coding agent built with React and Ink. !GitHub Repo stars

Local-first observability for AI coding agent sessions, tool use, skills, and costs ☆103

🦀 🏠 - Coding agent with basic list, read, replaceinfile, write, executecommand and web search tools. Supports multiple projects concurrently.

🏎️ 🏠 🐧 🍎 🪟 - Containerized environments for coding agents. Multiple agents can work independently, isolated in fresh containers and git branches. No conflicts, many experiments. Full execution history, terminal access to agent environments, git workflow. Any agent/model/infra stack.

An agentic debugging MCP server that helps AI coding agents delegate and fix bugs using multi-agent hypothesis testing.

An open-source, workflow-first terminal coding agent with subagents, skills, sandboxed tools, and multiple model providers.

A DeepSeek-native terminal coding agent in Rust with OS-level sandboxing, persistent goal mode, background tasks, and verification gates !GitHub Repo stars

Context runtime and MCP server that reduces AI coding agent token costs via session caching, AST-aware compression, and shell output patterns. Website

Coding agent that lives in your browser, hooks into your dev server, sees the live DOM, component tree, CSS, routes, and logs, then edits the actual source files with instant hot reload. !GitHub Repo stars

A local, open-source coding agent for developers who are tired of vague skill claims, token-saving extensions with no evidence, and agents that change a repository before understanding it. !GitHub Repo stars

Local-first multi-agent desktop application where a Commander coordinates specialist agents for research, coding, data analysis, documents, and media; MIT-licensed with bring-your-own model keys. !GitHub Repo stars

🎖️ 📇 - Automatically converts feedback and bug reports from websites and web apps into actionable, context-enriched developer tasks. Delivered straight to your AI coding tools, the Webvizio MCP Server ensures your AI agent has all the data it needs to solve tasks with speed and accuracy.

DeepSeek's official setup guides for integrating its models with coding agents including Claude Code, Codex, Cline, OpenCode, and Pi.

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.

Self-evolving AI coding intelligence with infinite memory (TurboQuant), genetic algorithm self-evolution, predictive bug detection, PageRank knowledge graphs, swarm intelligence, and adversarial defense.

A lightweight, powerful framework for multi-agent workflows

📇 ☁️ 🏠 🍎 🪟 🐧 - Meta-MCP server that unifies multiple AI coding assistants (Codex, Claude Code, Cursor, Gemini) through intelligent auto-discovery and standardized MCP interface, providing zero-configuration access to the entire AI coding ecosystem.

Educational framework exploring ergonomic, lightweight multi-agent orchestration by OpenAI. !GitHub Repo stars

🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org

Zero-config MCP unifying multiple AI coding assistants ☆123

Git-Native Agent Protocol: coordinate AI agent teams with 4 JSON files in a git repo. No server, no database. Any agent that can git push can participate. MIT licensed.

Jira tickets info for AI coding agents ☆26

🏎️ ☁️ 🐧 - A simple memory tool for coding agents using DuckDB and VoyageAI.

🐍 ☁️ 🍎 🪟 🐧 - Agent-to-agent referral network where AI agents discover, recommend, and refer users to each other. Features bilateral trust model, credit economy, and 7 MCP tools for agent registration, discovery, and referral tracking.

🐍 ☁️ 🏠 🍎 🪟 🐧 - Agent-to-agent marketplace middleware — MCP-native discovery, negotiation, and transaction between AI agents

Agent multiplexer for running dozens of parallel Claude Code sessions with a web dashboard, self-healing watchdog, kanban board, agent-to-agent REST API, and mobile PWA. Python 3 + tmux. !GitHub Repo stars

🐍 ☁️ - Query articles, verified statistics, wire feed, and social tools from The Agent Times, the AI-native newspaper covering the agent economy. 13 tools including search, comments, citations, and agent leaderboards. No API key required.

GitHub

github.com

</details>

An AI coding engine for complex tasks !GitHub Repo stars

49 production-tested AI agent system prompts for Claude Code multi-agent orchestration with retrieval-augmented generation patterns. MIT licensed.

🐍 🏠 🍎 🐧 - Bring structure and preserve context in vibe coding by automatically tracking issues.