Code agents

CLI for the frites multi-agent gateway and coding council

AI mission workflow toolkit with a px CLI — local-first, human-in-the-loop multi-agent development

Agent Multiplexer -- multi-agent coordination for AI coding agents

Multi-agent orchestration for AI coding assistants (Claude Code, Codex, Cursor, Gemini CLI)

OpenCode plugin for dynamic multi-agent workflows via JSON DSL

Verified Loop multi-agent system for rigorous research and development in opencode and Claude Code

SynapseXcoder V6.0 - Multi-Agent OpenCode Plugin & TUI Framework with 13+ Specialized Agents, Knowledge Vault, Security Audit, and Verification Engine

Coral-backed multi-agent research CLI with a SQLite blackboard and Delve-style negotiation.

Multi-Agent Orchestration Platform — coordinate, observe, and audit swarms of AI coding agents via a shared MCP server

Zelari Code — AI Council coding agent CLI. Multi-agent orchestration (Caronte, Nettuno, Gerione, Plutone, Minosse, Lucifero) with slash commands, provider-agnostic LLM streaming, and self-update.

Sync and inventory multi-agent skills and MCP configs from .agents/ manifest

MCP memory server for multi-agent systems, powered by Postgres, pgvector, and Hugging Face.

Core framework for multi-agent pipelines: governance, memory, orchestration, verification, trust tiers, and multi-platform support

Framework-agnostic multi-agent scaffold for Claude Code — install once, run cls init on any project

Enhancement framework for Pi CLI coding agent — transforms the raw agent into a coordinated multi-agent orchestration system

Spec-first workflow: integrates OpenSpec planning engine + Superpowers execution discipline via bridge contract. 9 collaborative skills for multi-agent coding tools.

Multi-agent orchestrator for Claude Code. Track work with convoys, sling to polecats. The Cognition Engine for AI-powered software factories.

Multi-agent swarm coordination plugin for Claude Code

Multi-agent orchestration system for Claude Code - maintain architectural integrity at scale

Multi-agent swarm framework on the Vercel AI SDK — model + process agents, LLM planner, blackboard, actor/verifier loops, budget governor, topologies. CLI + MCP + REST.

Multi-agent workflow orchestration CLI for Claude Code - scaffold projects, define tasks, spawn agents, and automate development workflows

The Codebase Immune System - Autonomous multi-agent governance for GitLab repositories

Openbuff SDK - AI coding agent framework

Nexia — multi-agent framework for end-to-end legacy system modernization. Installs agents and skills for Claude Code and Codex CLI.

A high-velocity harness for agentic development

Excalibur CLI — local-first AI-assisted and agentic development from the terminal

an agentic coding CLI

Version-aware open-source context for agentic software development

UTIM AI CLI – Universal Terminal Intelligence Manager. An agentic AI coding assistant for your terminal.

Agentic CLI to benchmark and audit repositories and review/resolve pull requests against industrial-grade standards.

Groundwork policy, provenance, context, and risk foundations for agentic development tools

Benchmark and observability harness for comparing agentic coding tools.

Local Studio cockpit for AI-built apps: agentic chat, provider context, release review, diffs, and approval-controlled repo work.

Token-optimized agentic framework scaffolder with pi-first architecture

Agentic job-search workspace for finding, vetting, tailoring, tracking, and preparing for roles.

JUWEL CLI — an agentic coding assistant that verifies its own output. Runs an agentic tool loop in your terminal, then runs post-turn checks (types, tests, lint, arithmetic, citations) over the files it touched; blocking failures feed the next turn so it

Integrated Vector Cadence skill suite for agentic software engineering workflows.

Agentic Memory CLI — persistent memory for AI agents. As easy as git.

Governed Agentic Development Framework CLI (prj). A bash CLI wrapped for npm; operates on a governance workspace resolved via $ADF_WORKSPACE or the nearest org-config.yaml. Runtime prerequisites (not npm deps): bash, git, gh, yq, python3 (use Git Bash on

Aeonyx Code — an agentic coding CLI for your terminal.

An open source local-first terminal coding agent. Peer programming with any frontier model or local/free models to run agentic development.

Auto stage→commit→push for agentic engineers. Works with any coding agent.

Pluripo — the agentic terminal coding agent.

Oxagen CLI — agentic coding powered by Oxagen's knowledge-graph context engine

AI-native team operating system workflow compiler for OPT teams.

Sparrow — spec-driven DDD framework for AI coding assistants. Generate structured skills that guide AI agents through domain-driven design, from business requirements to production code.

Managed Deep Agents — the `defineDeepAgent` authoring interface plus the CLI that compiles and deploys a code-first Deep Agent repository to a managed LangGraph runtime.

Multi-agent orchestration framework for Claude Code CLI. Run agents in parallel (Conductor) or stateful workflows with crash-resume + Human-in-the-Loop (Conductor-LangGraph). Subscription-flat by default.

A local-first coding agent that keeps small local models focused instead of hallucinating.

Deterministic workflows of agents — a Docker-Compose-shaped YAML for composing LLM / code / model / tool nodes into a runnable flow.

Unified MCP server, skill, and hook registration across coding-agent platforms

Local-first failure diagnosis for AI browser automation, Playwright, crawler, and RPA runs.

Repository maintenance checks and diagnostics for AI-assisted Python development.

Release-readiness gates for AI agents: replay a pack of constructed safety scenarios, apply policy-as-code gates, and produce ship/warn/block evidence before an agent, prompt, model, or tool-policy change ships.

Deterministic safety hooks for Claude Code

A lightweight global Markdown spec and decision vault for AI coding agents.

AI Agent Token Saver - 减少多 Agent 平台 token 消耗的综合工具（支持 Claude Code, Codex, OpenClaw, Cursor, Aider, Continue, Windsurf）

Agent-hook safety gate for AI-written code -- blocks bidi/invisible Unicode and CJK corruption at the write boundary

An elite autonomous coding and DevOps agent powered by Gemini 2.5 Flash

Free, open-source observability for AI agents. Trace LLM calls, catch silent failures, score output quality.

Agentic RAG over consent-gated Web3 documentation — search and answer developer questions from Ethereum, Solidity, and ecosystem docs.

A sequential crew of AI agents that clean up your codebase.

Static security scanner for agentic AI configuration: settings, permissions, hooks, MCP servers, agents, skills, and steering files (Checkov for AI agent stacks).

Static security scanner for AI coding agents and MCP configurations

Make sense of what your AI agents did — local-first, MCP-native observability, trace replay & trajectory diff.

Time-travel debugger and branch explorer for LangGraph AI agents. Capture execution traces, inspect LLM and tool calls, and branch from any point with overridden outputs.

Тонкий harness-фреймворк для AI-агентов: сменный провайдер рантайма (API/Claude Code/Codex), middleware-pipeline и слой skills/MCP.

Small metadata and URL helpers for AI Agent Skills, a curated Claude, Codex, and AI agent skills directory.

Git for LLM context. Snapshot a dying session, brief the next model in 30 seconds.

Bark notification hooks for Codex, Claude Code, and OpenClaw agents.

Python SDK for BaseCodeAgent — discoverable AI agent services on Base with x402 payments

Run your coding agent in a bubble.

Local session-history browser, token/cost analytics, and productivity insights for Claude Code.

A zero-dependency Python module for inspecting and converting Claude Code session files (.jsonl) into the messages format expected by Hugging Face Transformers.

Cost-aware model routing for the Claude API — reference implementation with a Claude Code subagent hook

Standalone, dependency-light verifier for CloakLLM audit artifacts -- verify hash chains, Ed25519 signatures, key provenance, RFC 3161 timestamps, and compliance reports WITHOUT the full SDK or trusting CloakLLM's code.

Cloud-Dog agent strategy primitives (PS-96) + prompt-engineering (D5) + per-LLM format adapters (W28M-1601): codeact/react/reflexion arch + adapters reconciled (0.3.2)

一款纯净的自主 Agent 系统。

AI Powered DevOps RCA Agent

本地私有知识库 MCP 工具：把文档与代码仓库导入本地向量库，供 Claude 等 MCP 客户端语义检索；纯本地、数据不出机，支持后台导入、80+ 文件类型与 Office 文档

LangChain chat model wrapper for the Claude Code Agent SDK — Mimir distribution of langchain-claude-code with bundled adapter fixes (upstream PRs #2/#4/#6, unmerged). Import package remains ``langchain_claude_code``.

Docker sandbox backend for AI agents - execute code safely in isolated containers

Gateway-agnostic core for llm-catalog: config schema, resolver, GatewayTransport, and LiteLLM codegen. Knows nothing about any runtime adapter.

A coding agent built on LLM

The persistent memory layer for AI coding agents

LLM-as-judge linter: enforce code-quality checks deterministic linters can't express, by driving real coding harnesses through oneharness.

Interactive viewer for Copilot and Codex coding-session token usage

CLI-first, local LLM cost tracker for indie devs — drop it in front of any OpenAI-compatible API and watch token usage and spend in real time. No cloud, no signup.

The acceptance layer for autonomous coding — 'CI for AI agents'. A swarm works until a verifier PROVES the goal is done.

Portable MCP code-map server for token-efficient coding agents

A modern AI coding agent with RAG, ACP, and smart context management

Meterbility SDK for Python — trace LLM agent runs into the local Meterbility store

MCP server for reading Claude Code session history from the local filesystem

Catch the LLM/AI calls you didn't need. A fast, deterministic linter that flags LLM API calls where plain code is simpler, cheaper, and more reliable.

Host-agnostic, self-correcting library/API memory daemon for coding agents (Qwen MemoryAgent)

A clean-architecture RAG library with graph orchestration, multi-provider LLMs, and a low-code facade.

Universal RAG framework SDK for Python developers

AI-powered ROS 2 development assistant

AI-агенты как сущности: автономный онбординг инструкций (идемпотентные managed-блоки в .claude/.cursor/.codex/.gemini/.github/…) поверх единого реестра агентов-данных. Тонкий слой на clikit.

A coding agent with history-bounded, task-elastic reconstructed context — built for long-horizon work.