Code agents

Multi-agent orchestration across pi sessions

Cost-aware, local-first routing plugin for opencode with cheapest-capable frontier fallback and multi-agent orchestration.

Global installer for the coordinator + coord-worker Claude Code skills (multi-agent coordination playbook).

Numex AI Core Engine — Multi-agent council, RAG, vision, NCP plugins

OSS-first engineering harness for deterministic, spec-driven, issue-driven, audit-governed and orchestration-first multi-agent software delivery.

Decentralized LAN multi-agent collaboration node — AI-controllable enhanced LocalSend (去中心化局域网多智能体协作节点)

Coding-agent orchestration and MCP context runtime with governed repository execution, bounded tool results, and multi-agent session management.

Dependency-aware multi-agent workflow CLI for OpenCode.

Fork: Pi extension for single-agent delegation and scripted multi-agent workflows

Provider-agnostic Model Context Protocol (MCP) collaboration server: claim files, persist working memory, and prevent multi-agent session conflicts

Lifecycle orchestration engine for AI agents — 28 stages, adaptive scope, agent framework mode

Agentic HQ - Orchestrating agentic software development teams

Scaffold and manage team Agentic Dev Environment (ADE) knowledge repos

Production-grade Playwright + TypeScript Scaffold for Agentic Testing. Harness for all major AI coding agents baked in.

pi extension that mirrors every session entry into an @agentic-kit/run-log store, verbatim and in order

Installer package for Nexus-DevFlow agentic workflow layer.

pi extension that routes model calls through the Constructive metered gateway, so a pi session is metered exactly like agentic-server traffic

BDB Creator Extension - Agentic Media Pipeline

A controlled workflow for agentic software development.

Bee Code - an agentic coding assistant for your terminal, from HEOSSI.

Vinaya — Agentic Engineering Harness. Deterministic checks every AI coding agent must satisfy before merge.

Multi-Chain CLI Wallet (MCW) & Agentic Framework for Humans and AI Agents (MCP)

Placeholder — see https://agentic-atlas.dev

Enterprise-Grade Closed-Loop Agentic Orchestration Engine & Spec-Driven Verification Framework for AI Coding Agents.

Workit — workflow rails for agentic coding: specs, plans, YouTrack, CI-gated commits (shared core)

Discovery + management wrappers around the gh CLI for AI coding agents. Ships as a standard agent skill, an Agent Plugins 1.0 plugin (plugin.json + skills/), and a dsh plugin (dsh.bundle.patch registers the skill at runtime).

MCP server that sells verified dev-error fixes to AI agents. Paste an error, get the fix — free search, 3 free samples, ~$0.08 on-chain. Works with Claude, Cursor, Codex, VS Code, LangChain, CrewAI.

Developer CLI and shared toolkit for the Enterprise AI Workspace (Angular studio, NestJS gateway, LangGraph agent-core). Includes architecture docs, gateway helpers, and an extensible Commander-based CLI.

MCP server for NexusGenesis agent-keys — zero-code key management for Claude Desktop, Cursor, LangGraph

Lightweight provider-agnostic agentic coding backend (CLI + server) for the NanoCode VS Code extension.

Connect your local agent (Codex, Hermes, …) to AG2 Space as a first-class room agent.

Inter-agent messaging bus for Claude Code, Grok, OMP, Codex and others

Token, cache and context observability for AI coding agents.

Catalog-backed API key loader for coding agents

A deterministic, subscription-aware coding agent scheduler

Time-travel debugging for AI agents — OTel-in / replay-out.

Capture coding-agent transcripts to disk and expose them as SQL.

Keep AI coding-agent skills, instructions, permissions, and project history in sync from ~/.agents.

Ultra-fast, zero-bloat Minimal CDP Browser MCP in Python for AI coding agents

Ultra-fast, zero-bloat local markdown documentation RAG for AI coding agents via MCP

Intelligent context layer for Claude Code — infinite session memory, minimal active context

Sync Claude Code configuration from a git repo you own

claude-system — Python distribution wrapper (thin, bundles cli/dist)

Shared CLI conventions for agent-facing tools: exit codes, JSON output, skill installation, and the in-binary guide.

Distributed LLM inference — pool GPUs across multiple devices to run models no single machine can handle

τ-coding-agent: Interactive TUI (Textual) + CLI

Search, hire, and dispute other agents autonomously from inside your own agent's code — authenticated with the AgentCredential gora8 already gave you, no separate setup

Re-registers the dormant ACP_BACKEND_CLAUDE seam so KiroCrew runs on Claude Code

LangChain tool for executing untrusted code in Microsoft Hyperlight micro VMs (experimental, AI-generated)

Declarative runtime-state management for a LiteLLM proxy: reconcile users/teams/keys/credentials/models from a YAML spec.

Is your llama.cpp decode memory-bandwidth-bound? Measure it, in one command.

A programmable layer for unattended AI coding work: drive Claude Code, Codex, and Gemini CLIs from a YAML playbook with verify/repair loops, budgets, cross-agent fallback, and usage-window riding.

Open-source debugger for AI agents.

A key-addressed retrieval system for coding agents

A lightweight RAG debugging toolkit: understand why your RAG application gave a bad answer.

Subagent MCP gateway for Codex to orchestrate external coding agents through native harnesses.

Universal AI agent plugin build tool

DSL-driven web AI agent for file operations, code modification, and command execution

Terminal AI agent for code operations via Moonshot or DeepSeek API

A headless local runtime that connects installed AI agent CLIs to any program, with MCP tools and permissions

Privacy-first AI agent bridge with native Feishu Card 2.0 streaming

Modular CLI tool featuring LangGraph AI Agent, file compression, string manipulation, and API integrations

**The AI agent that contributes to its own development.**

AI agent detection plugin for Bunli - detects Claude, Cursor, Copilot and other AI coding assistants

Define arbitrary workflows in TypeScript and run them inside the PI coding harness.

Unified MCP server for multi-LLM consultation — routes Gemini, Codex, Claude, Grok, Ollama, and Antigravity behind runtime availability checks

LangChain.js adapter for CodeSpar — convert session tools to LangChain StructuredTool format

A lightweight, customizable AI coding agent CLI — any model via OpenRouter; natively continues Claude Code and Codex sessions.

Custom pi coding-agent extensions: bwrap sandbox, workspace guard, opencode edit, and more

oFlow CLI - AI-powered terminal assistant for developers

Cache-first DeepSeek coding agent for the terminal.

ClinePass provider for pi — access GLM-5.2, Kimi K2.7, DeepSeek V4 and more open-weight coding models through Cline's $9.99/mo subscription

Loom Code — AI-powered coding agent for the terminal. Multi-provider support including NVIDIA. OpenTUI interface.

CLI coding agent with OAuth authentication for Anthropic, OpenAI, and Gemini

Use a ChatGPT Codex subscription in DeepSeek Harness through standalone OAuth

Lightweight coding agent with selectable restricted or native workspaces and optional remote executors.

Local-first CLI for connecting coding agents to Dharma evaluation, orchestration, and signed Skill delivery

The security-native AI coding agent. Six Sec-Test security personas, compliance-first /scraper, a business documents & research suite, and multi-agent Compose orchestration — spec-driven workflow engines in one terminal-first CLI.

quantum-spherifier (:qSpherifier) v1.0 — Autonomous Scientific Research Agent for Quantum Computing. Built on the Artificial Junky Neuron (AJN) framework, extended from predator-jungle-agent v2.0 via fusionary-agent by Justo Tapiador Garcia (UA). Generate

ToolNet CLI — AI coding agent for the terminal

41 Product Design Agent Skills for AI coding agents. Covers Visual Intelligence, Product Thinking, UX, UI/Design Systems, Modern Platform Patterns, Responsive, QA Autonomous, and Growth-Aware workflows. Compatible with Claude Code and Google Antigravity I

OpenCode goal plugin for persistent autonomous multi-turn coding agents with host-verified completion, restart recovery, and /goal workflows.

Codex-inspired background goal engine for OpenCode — autonomous subagents, engine-driven loop, child worker sessions and modal TUI dashboard. Like Claude Code loop for OpenCode.

Fast, provider-agnostic AI coding assistant — BYOK, any provider, all from your terminal.

Deep Ideation, Multi-Agent Deliberation & Systematic Thinking Engine for AI Coding Agents

Rose: The Advanced Agentic Coding Assistant, platform with tools, memory, automation, research, multi-agent orchestration and Gemini Live.

Live terminal debugger and offline ASCII graph renderer for LangGraph.js — no LangSmith account, no network calls.

Watches the third-party APIs a codebase calls and opens verified pull requests when one breaks. Docker if you have it; a user-space install if you do not.

Fast, accurate agent-to-Android control over plain ADB: semantic UI addressing via uiautomator, no on-device install

Unified detection, configuration, and chat discovery registry for AI coding agent CLIs

Deterministic cross-language guardrails for agent-assisted development

Run Codex CLI and OpenCode CLI simultaneously on isolated git worktrees - LLM task planner, parallel headless runners, auto-merge

The Unified, Non-Destructive Model Configuration & Snapshot Manager for AI Coding Agents.

Run coding agents in a per-project dev container sandbox.

AgentInfoView (AIV) — a presentation surface & feedback channel for coding agents. Name reserved; project in active development.

Lightweight, security-first converter between coding-agent config formats (CLAUDE.md, AGENTS.md, Cursor rules, MCP configs, SKILL.md).

ATIF-based reference implementation for portable coding-agent trajectories with explicit fidelity and loss reporting.

Summarize & export a Claude Code session into one clean handoff.md for Gemini, GPT, or another Claude.

A focused terminal workspace for collaborating with ACP coding agents.

Evidence-driven local autonomous software engineering agent