Code agents

Terminal-native autonomous AI coding agent with client-side tool execution and DLP guardrails

Repo-issue–driven autopilot runner

Frozen released-v1 Session codec and assistant-stream migration to v2

A shared record for AI agents: decisions, completed work, and commitments, with sources. Git-native engineering memory and a self-hosted state server.

GitLab OAuth authentication plugin for OpenCode

The **[Fish Audio provider](https://ai-sdk.dev/providers/ai-sdk-providers/fish-audio)** for the [AI SDK](https://ai-sdk.dev/docs) contains speech generation (S1 and S2 models) and speech-to-text transcription support.

Qoder provider plugin for OpenCode powered by the official Qoder Agent SDK, with streaming, tools, MCP, sessions, multimodal input, and quota tracking.

The **GMI Cloud provider** for the [AI SDK](https://ai-sdk.dev/docs) contains language model support for [GMI Cloud](https://www.gmicloud.ai), offering GPU inference for open-weight models over an OpenAI-compatible API.

A chat for Main Sequence Agents: the connection to the platform, a session engine, the chat UI, and model provider settings, built on the Command Center SDK.

Self-hosted AI Assistant plugin for NodeBB forums with automated unprivileged bot provisioning, multi-model fallback resiliency, thread history context, Unicode/Hebrew mention parsing, RAG, and support for Gemini, Grok, Claude, OpenAI, Groq, DeepSeek, Oll

KXM local-first multi-agent orchestration and operator dashboard

Adaptive Multi-Agent Orchestration with Cost Intelligence for OpenCode V2

Persistent in-process Codex-style multi-agent collaboration for Pi

Remote multi-agent development workspace for the official Claude Code and Codex CLIs

Enterprise-grade spec-driven development framework for multi-agent workflows

Interactive CLI runner for H0wZy/mcp — The Ultimate Multi-Agent MCP Hub

Native multi-agent hub: Claude Code, Codex, Kimi Code, Pi and local inference as peers in one project

Olives Technologies Engineering OS — Autonomous Multi-Agent AI Engineering Environment

Durable multi-agent coding runtime for Pi, Claude Code, Codex, and Specialists

Behavior OS - Workflow Operating System for governed multi-agent development

Remote multi-agent development workspace for the official Claude Code and Codex CLIs

Remote multi-agent development workspace for the official Claude Code and Codex CLIs

Remote multi-agent development workspace for the official Claude Code and Codex CLIs

Multi-agent development workflows for CodeBuddy, Codex, Cursor, and Claude Code

Remote multi-agent development workspace for the official Claude Code and Codex CLIs

Multi-agent extension for pal — delegate tasks to specialist sub-agents

TUI-first, document-driven multi-agent coding runtime

opencode multi-agent bus: agents ask each other questions over a shared SQLite queue

Sandboxed multi-agent workflow runs for OpenCode V2

dulger — a multi-agent kanban orchestrator that wraps Claude Code / Codex

Bun-native coding agent with OpenTUI, persistent sessions, policy-controlled tools, MCP, and live multi-agent orchestration.

Human-governed project discovery, planning, multi-agent orchestration, and durable resume.

Laila: An advanced, local-first AI developer assistant with MCP, Vision, and Multi-Agent Swarm capabilities.

A maximalist, model-agnostic coding harness for the terminal, with lazy skills, tools, MCP and multi-agent orchestration.

Route Codex prompts or run a visible multi-agent Codex team

Open-source multi-agent roundtable code review engine (CLI-first).

Sandboxed multi-agent workflow orchestration, plus a deterministic multi-angle code review built on it.

Codex-style collaboration for Pi: spawn_agent, followup_task, send_message, wait_agent, list_agents, and interrupt_agent. Named agent trees, configurable child model, history forks, mailboxes, and a packaged multi-agent-mode skill.

A spec-first, multi-agent AI coding pipeline you drop into any repo. The law your agents work under.

Reusable multi-agent harness for AI-assisted development: personas, skills, operating rules, model routing, and QA gates. Deploy into any project with `npx @dombaras/agent-harness init`.

Power Take-Off for AI agents — governed multi-agent engineering workflows over interchangeable agent CLIs.

A multi-agent harness generator: one persona spec (SOUL.md) compiled into Claude Code, OpenCode, Cursor, and Antigravity native agent/rule formats.

Portable multi-agent workflows for Claude Code, Codex, Pi, OpenCode, Kilo Code, and direct API runners.

Multi-agent coordination protocol for AI coding tools

Enterprise-grade OpenCode plugin with micro-plugin architecture, multi-agent orchestration, and professional naming

Local multi-agent squads for Claude Code, Codex, ZCode, Kimi Code and any MCP host

radical-code — Rust AI development framework CLI: setup wizard (config.db + encrypted secrets vault), TUI, REPL, multi-agent dispatch, MCP brain.

Multi-agent debate orchestrator plugin for OpenCode — Captain + parallel sub-agents + dynamic debate rounds + early stopping

Hierarchical multi-agent plugin for OpenCode Desktop — imperial government structure with Emperor, Prime Minister, Six Ministries, and deep subagent nesting.

A DSH port of obra/superpowers — the full multi-agent software-development methodology (TDD, planning, debugging, review) as native DSH skills

Guided feat/bug workflows (start→ship), post-deploy monitoring and multi-agent code review, stack-agnostic. Each repo uses a shared FLOW.md plus optional harness overlay.

Unified access layer for RDS ContextDatabase: `ctxdb` CLI (memory + KB ops), one-shot multi-agent installer, per-agent config, hooks/plugins, and SKILL.md.

Multi-agent development orchestrator — autonomous task planning, execution, and validation with Claude Code integration

A multi-agent orchestration workflow for product and engineering. Host-agnostic skills, per-repository adapters, and a knowledge vault that learns.

ProofBridge: a multi-agent CLI workspace and cross-provider collaboration layer.

A model-agnostic terminal coding harness with multi-agent collaboration

AI context layer and multi-agent coordination center for any repository, exposed over MCP.

Adaptive Director Skill — Skill-first adaptive multi-agent orchestration for AI coding agents

Worca — deterministic multi-agent pipeline that drives Claude Code (headless) through Plan -> Refine -> Implement -> Review, with a CLI, an installable /worca skill, and a web UI.

Reusable Ralph workflow pattern - ticket-driven development with multi-agent review loops

Stateful multi-agent orchestration system for Claude Code, and an npm-installable OpenCode plugin

Tool-agnostic, packageable multi-agent + subagent framework. Generic agents, on-demand subagents, knowledge from skills/instructions, codebase auto-init.

MCP server for iOS Simulator, Android Emulator and headless web control. 124 tools: device automation (tap/swipe/type), accessibility audits, visual diff, crash logs, App Store / Play Store pre-submission compliance, offline CVSS scoring + dependency inve

Local-first, multi-agent Astro website builder for Claude, Codex, Antigravity, and the command line.

/code-review slash command for DeepSeek Harness — multi-agent review of pull requests and local code, with configurable confidence scoring

TopWord — next-generation CLI agent framework (State-Manifold paradigm)

Eliza - the agent framework - name reserved; first release in development.

TopWork — next-generation CLI agent framework (State-Manifold paradigm). Work in progress.

Code-only agentic design system: contracts, tokens, and React components.

Long-term memory for agentic tasks. It tells you when it doesn't know.

Guardrail extensions for Agentic Driver: advisory review, bounded Herdr communication, and guarded worker lifecycle.

OpenSpec agentic workflow extension: schema, role models, installation and migration.

Agentic coding assistant

makecli — agentic development platform cli

Scaffolds an agentic/ directory (skills, agents, hooks, tasks) with .claude and CLAUDE.md symlinks, and seeds a ticket-to-subtasks pipeline

Syntax & Syllogism agentic loop runner.

Pluripotent stem-cell framework and universal agentic toolchain for autonomous workflows

Portable agentic SDLC, policy and evidence evaluation for developers and CI/CD

The DemoBites agentic recorder — you prompt, it films a real browser, and DemoBites turns the take into an editable demo bite.

Shopware 6 agentic harness: sw-* skills and sub-agents, plus an installer that writes them into Claude Code, Codex, GitHub Copilot and Cursor.

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

Corsair tools for LangChain.js / LangGraph — expose 200+ integrations to your agents with managed OAuth and credentials that stay in your own database.

Agent skill for debugging LangChain and LangGraph applications by fetching and analyzing LangSmith traces.

MCP server that builds a reachability graph across multi-agent orchestration configs (LangGraph, CrewAI, AutoGen/ag2) to find transitive excessive agency — an agent with no dangerous tool of its own that can still reach one through delegation or group mem

Codex login and session management for the abstract toolserver

Transparent, framework-agnostic assurance checks for AI agents, mapped to OWASP Agentic security standards.

A real-time tool-call firewall for AI agents, built on TypeSafe's Jev.

Local message bus between terminal coding agents: Claude Code, Codex, Muse, OpenCode, Pi, Cursor

One interface through which a coding agent spawns agents on any harness and exchanges messages with them

Framework-agnostic Python library for diagnosing LLM agent execution failures

Deterministic benchmark harness for command-line coding agents

See what your AI agents are actually doing. Local-first tracing and debugging for AI agents.

Checkpoint-gated developer/reviewer loop across Claude Code, Codex, Grok, and Antigravity CLIs.

Official Python SDK for the Agent Margin Router API – one pay-per-call endpoint for web, market, on-chain, DeFi and developer data. Pay with USDC on Base via x402, or use an API key. 3 free calls per wallet.

Keep agent plugin and marketplace versions in sync.

Local memory, a codebase index, and working discipline for AI coding agents. Zero dependencies, no network.

Autonomous behavior firewall, vendor-agnostic control plane, and permanent memory across Gemini, Claude, Codex, Copilot, Cursor, and Windsurf

Agent orchestration patterns over long-running coding agents

Run several coding agents in isolated worktrees with shared coordination.

A local IPC mesh so any AI coding agent harness (Claude Code, Codex CLI, Antigravity, pi, opencode, ...) can find, message, and reactively wake up any other.