coding-agent — independent software & tools
-
agentty
AI pair programming in your terminal — one static binary, sub-ms startup, any model
-
CodeyBox
Runs CLI coding agents (Claude Code, Codex, Copilot, Cursor, Gemini, opencode) against a task queue. Each works in an isolated VM; output is checked by configurable auditors, then merged via git. Pools multiple provider subscriptions with quota-aware routing and fallback. C#/.NET 10, MIT-licensed.
-
Codeably
Autonomous coding agent. Bring your own API key. 7 providers. Zero cost forever.
-
Dezin
A local-first, tasteful design generator. Describe what you want; your own coding-agent CLI (Claude Code, Codex, Gemini, Cursor) builds it as a real artifact, held to a strict anti-AI-slop standard. BYOK, nothing leaves your machine.
-
telegram-ai-monitor
Track Telegram messages with AI, classify them in real time, and view alerts and insights in a React dashboard.
-
my-opencode
OpenCode configuration with agents, skills, review guardrails, and a GitHub Issues workflow bundle.
-
large-codebase-survival
Manage large codebases with AI agents using a proven methodology to prevent context window overflows and session crashes.
-
claude-code-memory-setup
Reduce token usage and add long-term memory to Claude Code using Obsidian and Graphify for efficient codebase awareness.
-
telegram-ai-scope
AI-Powered Telegram Monitor 2026: Real-Time Message Classification & Insights Dashboard
-
M31A
The terminal-native AI coding agent that ships, not just suggests. Six-phase workflow, git rollback chain, zero telemetry. One static binary.
-
instincts
Working-instinct skills for Claude Code: verify claims against the source, log for the bug you can't reproduce, write like a human, test so the test bites. A reflex layer on top of superpowers.
-
kimi-K2.6
Build full-stack applications with an autonomous IDE using an agent swarm architecture powered by the Kimi 2.6 model.
-
agent-afk
Start a run in your terminal and walk away. Get pinged when it finishes, or needs you. Every step is a readable trace you check before anything ships.
-
ZhangXueFeng-skill
提供高考志愿填报的决策支持，通过模拟张雪峰的思维方式和数据分析框架，帮助用户获取关键信息并做出理性选择。
-
Forge
Self-hosted AI coding orchestration dashboard with an Orchestrator, worker queue, providers, GitHub CLI tooling, and local/cloud LLM support.
-
app
One Works application monorepo for AI agents, plugins, desktop, web, CLI, and Relay.
-
CommandNest
Access desktop AI tools from your menu bar with a lightweight, cross-platform assistant.
-
claude-code-ripper-rs
PikoClaw 2026: Rust-Powered AI Agent for High-Performance Devleopment
-
vibe-codr
A model-agnostic CLI coding agent for the terminal — any provider (Anthropic, OpenAI, Ollama, 20+ more), plan/execute/yolo modes, subagent orchestration, and long-term memory. Bun + TypeScript.
-
diffgate
Triage for AI-generated code review: grades each changed diff line green/yellow/orange by impact, so reviewers spend attention where it matters. High-signal, low-noise (0 false blocks), deterministic — in your coding agent (MCP), editor (VS Code), and CLI/CI.
-
tokenctl
Hierarchical org→team→dev token-budget proxy for LLM traffic: meter, soft-throttle, hard-deny, and in-flight preemption across providers on one shared wallet.
-
Do-SOUL-Alaya
The local-first memory plane for CLI coding agents. Codex and Claude Code attach via MCP; SQLite-backed, evidence-gated, no GUI. Cross-session memory that the agent proposes and a governance gate decides.
-
wizard
Self-extending autonomous agent in one Rust binary. One-line install, any provider (OpenAI-compatible, Anthropic, xAI) or fully local via llama.cpp, live /evolve self-modification, MCP, messaging gateway, built-in bench
-
acpx
Headless CLI client for the Agent Client Protocol (ACP) — talk to coding agents from the command line
-
clavue
Clavue: execution-first AI coding CLI with direct repo tools, provider routing, native workflows, MCP integration, and long-session recovery
-
@hypabolic/hypa
Local context runtime for coding agents: compress shell output, query code, and proxy MCP tools
-
@kilocode/cli
The AI coding agent built for the terminal. Generate code from natural language, automate tasks, and run terminal commands -- powered by 500+ AI models.
-
omnius
AI coding agent powered by open-source models (Ollama/vLLM) — interactive TUI with agentic tool-calling loop
-
pi-mcp-adapter
MCP (Model Context Protocol) adapter extension for Pi coding agent
-
sanook-cli
A terminal AI coding agent — BYOK, 9 providers, MCP, cron gateway, skills, and git awareness. Built from scratch in TypeScript.
-
@trymesh/cli
Mesh terminal agent CLI — token-efficient coding agent with a shared LLM gateway.
-
AIDOCS
AIDOCS — AI Doctrine Orchestrator, Control & Security.
-
Push
Run your repo from a chat — the git tool that feels like your AI app. Collapses GitHub, terminal, CI, code, and AI into one conversation. Mobile-first, self-hosted, provider-flexible.
-
codeflare
The enterprise agentic engine. Governed engineering agents that build, test, review, and operate inside your own estate. Spec-driven, attributed, and encrypted.
-
code-buddy
Open-source multi-provider AI coding agent — terminal + Electron desktop (Cowork) + 24/7 multi-AI fleet, free-first on local Ollama. Opt-in, human-gated evolutionary self-improvement that ingests research to set its own goals. 15 LLM providers (Claude, GPT, Gemini, Grok), ~110 tools, MCP, voice+vision companion.
-
codeoid
Identity-first control plane for AI coding agents — multi-session, multi-frontend (TUI · web · Telegram), with cross-session memory and per-agent ZeroID identity.
-
iosm-cli
Provide a terminal-based AI tool to perform controlled, measurable engineering tasks directly on real codebases.
-
openskills
Universal skills loader for AI coding agents - install and load Anthropic SKILL.md format skills in any agent