Open Source Coding Agents
Discover 109 open source Coding Agent repositories from GitHub, each with an analysis of what it does, key features, use cases and alternatives. Coding Agent projects here are most often combined with AI Agents, Developer Tools and CLI. Last updated October 4, 2026.
109 repositories · updated October 4, 2026
claude-code-codex-bridge: Sync Claude Code Setup to Codex
A Python CLI that turns local Claude Code plugins, skills, agents, commands, MCP servers, and instructions into Codex equivalents. Useful for developers who maintain both tools and want Claude Code to remain the source of truth.
tmux-agent-sidebar: Monitor Coding Agents Across tmux
tmux-agent-sidebar brings Claude Code, Codex, and OpenCode activity from every tmux session and window into one sidebar. It helps developers track agent status, inspect work, and manage worktrees without switching panes.
codex-mcp-server: Connect Claude Code to Codex CLI
This TypeScript MCP server lets Claude Code call OpenAI Codex CLI for code analysis, generation, and review. It suits developers who want to use Codex alongside Claude in an MCP-compatible editor.
awesome-agent-skills: Find Skills for AI Coding Agents
A curated index of agent skills from official developer teams and the community, for use with tools such as Claude Code, Codex, Gemini CLI, and Cursor. Browse by provider and task to find reusable guidance for development workflows.
micstec-skills: Browse and Install AI Agent Skills
A managed collection of skills, plugins, extensions, rules, and MCP server resources for popular AI coding agents. Use it to browse materials across platforms and copy selected items into an agent's configuration.
skills: Ground Coding Agents in Azure and Microsoft SDKs
Microsoft skills provides reusable guidance, agents, and MCP configurations for coding agents working with Azure SDKs and Microsoft AI Foundry. Install only the skills relevant to a project to guide code generation with current domain patterns.
openinterpreter: Run Coding Agents in Your Terminal
Open Interpreter is a Rust-based terminal coding agent designed to get useful results from low-cost language models. It supports multiple agent harnesses and connects to ACP-compatible editors and Codex SDK clients.
agent-skills: Give AI Coding Tools HashiCorp Product Guidance
HashiCorp Agent Skills provides reusable guidance for AI coding tools working with Terraform and Packer. Install individual skills or product plugin bundles, and check the catalog for supported paths and lifecycle status.
a-mem-mcp: Build Evolving Memory for Coding Agents
A-MEM is an MCP server and Python library that stores agent knowledge as an evolving, connected memory graph. It suits coding-agent users who need to retrieve and build on project context across sessions.
agent-skills: Structure AI-Assisted Development from Specs to PRs
A collection of reusable skills for AI coding agents, covering specification writing, implementation, review, testing, and autonomous sprint workflows. Useful for teams that want repeatable processes and clearer quality gates across agent sessions.
agent-sandbox: Run Coding Agents in a Locked-Down Environment
Agent Sandbox runs AI coding agents in Docker containers with restricted workspace access and default-deny network controls. It suits developers who want to limit an agent’s access to local files, network services, and credentials while retaining CLI or IDE workflows.
Agent-Memory: Persistent Memory for AI Coding Agents
Agent-Memory gives coding agents persistent, searchable memory across sessions and tools. It is aimed at developers using MCP-compatible agents who want automatic context capture and recall without repeatedly explaining their projects.