Terminal-native coding agents

• Open Source

  • Codel
  • CodeMachine-CLI - agent CLI aimed at running coding workflows locally (vibe-coding oriented).
  • Letta Code - first CLI coding agent built on the Letta platform (formerly MemGPT); persistent memory across sessions, model-agnostic (Claude/GPT/Gemini), skill learning, and context repositories.
  • RA.Aid - full autonomy.
  • open-codex - provider support (OpenAI, Gemini, OpenRouter, Ollama).
  • Agentless
  • Amazon Q Developer CLI - 2.0.
  • Neovate Code - model/multi-provider support, MCP integrations, and headless automation mode. MIT.
  • Groq Code CLI - fast inference; extensible tools/commands with multi-model support.
  • Dexto - ready coding agent with sub-agent spawning.
  • g3 - running, repo interaction, skills system, and provider abstraction.
  • Coro Code - source CLI coding agent, a free alternative to Claude Code; generate, debug, and manage code seamlessly.
  • LettaBot
  • Mini-Kode
  • nori-cli - provider CLI built on Codex CLI; switch between Claude, Gemini, and Codex from the same native terminal.
  • cursor-agent - based agent replicating Cursor's coding assistant capabilities; supports Claude, OpenAI, and local Ollama models.
  • VibePod - config setup, local metrics, HTTP traffic tracking, and an analytics dashboard for side-by-side comparison.
  • QQCode
  • picocode - based coding agent focused on CI workflows and small codemods; multi-LLM with personas.
  • Smelt - provider (Anthropic, OpenAI, Ollama, GitHub Copilot, any OpenAI-compatible endpoint), four modes (Normal/Plan/Apply/Yolo), granular permission system, parallel subagents, vim keybindings, and headless scriptable mode. MIT.
  • Binharic - provider "tech-priest persona" coding agent CLI (stylized, tool-using).
  • Darce - model CLI agent built with Ink; 7 tools, smart model routing across providers, streaming, session resume, and slash commands. MIT.
  • CLAII - first AI coding agent with multi-agent orchestration, MCP toolchains, and memory-persistent refactors.
  • Claw Code - room Python/Rust rewrite of Claude Code architecture using oh-my-codex; fastest repo in GitHub history to 100K stars. Born from the March 2026 Claude Code source leak. MIT.
  • claw-code-agent - only Claude Code rewrite with zero external dependencies; born from the March 2026 Claude Code source leak, positioned as easier to hack on than the Rust/TypeScript reimplementations.
  • openHarness - source Claude Code alternative. 78 slash commands, 42 tools, MCP (stdio/HTTP/SSE + OAuth 2.1), hooks, subagents, plan mode. Works with Anthropic/OpenAI/Ollama/llama.cpp/LM Studio. Ships both npm and Python SDK. MIT.
  • Crab Code - native agentic coding CLI aligned with Claude Code's toolset and permission model; works with any LLM provider (Anthropic/OpenAI/DeepSeek/Bedrock/Vertex). 27 crates, 4,700+ tests, layered config system. Apache-2.0.
  • Octomind - source, model-agnostic AI agent runtime with community tap registry (`developer:rust`, `doctor:blood`, `legal:contracts`), MCP support with runtime self-extension, 13+ providers, and adaptive compression. Written in Rust. Apache-2.0.
  • Nanocoder - first CLI coding agent built by a community collective; bring your own model (Ollama, OpenRouter, or any OpenAI-compatible API), native tool calling with XML fallback, MCP support, and file-based custom commands and tools. MIT.
  • VT Code - source coding agent with LLM-native code understanding and robust shell safety. Supports multiple LLM providers with automatic failover and efficient context management. MIT.
  • zot - overhead and lightweight coding agent harness with TUI/JSON/RPC modes, structured tools, reviewable file diffs, skills, extensions, and optional guardrails.
  • San - native runtime for specialized AI agents; provider-agnostic (Anthropic, OpenAI, Google, DeepSeek, Moonshot, Qwen, MiniMax, GLM), runs Claude Code skills/plugins/MCP unmodified, swappable search backends, custom personas, sandboxed subagents, lifecycle hooks, and a self-evolving memory loop. Single ~12 MB binary, zero runtime deps. Apache-2.0.
  • Keen Code - based CLI coding agent focused on efficient context management — uses lean TurnMemory summaries instead of raw tool traces to maximize context efficiency. 9+ providers, skill-driven MCP servers, and full transparency with every prompt, design doc, and implementation plan saved as markdown. MIT.
  • Zap - first Rust TUI coding agent that injects only the context your task needs — no system prompt bloat. Single binary, no runtime. Supports Claude, Gemini, OpenAI, and local models via LM Studio; code-indexed via SQLite for fast symbol lookup; MCP support. MIT.
  • DvalinCode - neutral coding agent with three modes (Chat/Cowork/Code), inline diff approval, built-in Web GUI launched from a single binary. Works with any OpenAI-compatible endpoint (DeepSeek, OpenAI, Claude via OpenRouter, Groq, Ollama); macOS shell sandbox via `sandbox-exec`; `.dvalincodeignore` for sensitive files; `AGENTS.md` project memory. MIT.
  • Goose - device and integrate with MCP.
  • Deep Agents Code - in-the-loop approvals with any tool-calling LLM. PyPI `deepagents-code`.
  • MiMo Code - interactive modes, MCP, skills, hooks, git worktrees, and resumable sessions. Runs MiMo-V2.5-Pro or any mainstream provider; npm `@xiaomi-mimo/cli`. MIT.
  • OpenSquilla - hostable microkernel agent runtime with a full CLI (`opensquilla chat` REPL, one-shot agent mode, gateway); autonomous file edits, shell and background processes, git tools, ML-based tier routing, sandboxing (Bubblewrap/Seatbelt), persistent memory, and 20+ providers. Apache-2.0.
  • Codex Infinity - continuation, parallel multi-agent runs, and CI repair loops.
  • Waveloom - native coding agent with Bubble Tea TUI; DeepSeek V4 prompt caching for long-context efficiency; Claude Code-compatible UX with skill/MCP auto-discovery; four-tier context compaction, three subagent modes (Fork/Cold/Explore), permission engine, and plan mode. Single ~19 MB binary, zero runtime deps. Apache-2.0.
  • Grinta - first, provider-agnostic terminal coding agent built for long-horizon autonomous execution; durable state and recovery, context management, structured tool orchestration, LSP/DAP integration, and validation-gated completion. Python, MIT.