Orchestrates agents, memory, tools, and automated workflows around Claude Code and Codex.
Project overview
Ruflo is an agent meta-harness for Claude Code and Codex, adding specialist agents, swarm coordination, memory, learning, MCP tools, and hooks around development work. Its Claude Code plugin path only adds slash commands, skills, and agent definitions; it does not register the MCP server or hooks. The full npx init path installs the broader runtime, daemon, and orchestration features.
Build extensible coding agents with a unified model API
Project overview
Pi Agent Harness packages a unified multi-provider LLM API, a tool-calling runtime with state management, an interactive coding CLI, and a terminal UI as composable modules. It gives developers separate extension points for models, tools, and interfaces. Pi has no built-in permission system and inherits the launching process’s filesystem, network, and credential access, so stronger boundaries require a container or sandbox.
Run, switch, and automate coding agents across local and remote backends.
Project overview
OpenHands Agent Canvas is a self-hosted control center for running OpenHands, Claude Code, Codex, Gemini, and other ACP-compatible coding agents from one interface. It can switch among local, Docker, virtual-machine, and cloud backends and trigger engineering workflows on schedules or webhooks. A direct host installation grants full filesystem access. The code is currently moving to the software-agent-sdk and agent-canvas repositories.
Run and review multiple coding agents in isolated Git worktrees
Project overview
Superset coordinates command-line coding agents across isolated Git worktrees, with status monitoring, notifications, a built-in diff viewer, and one-click handoff to an editor or terminal. It works with several named agents and can accept any agent that runs in a terminal. Local development currently requires Bun, Docker, and Caddy, and downloadable Windows and Linux builds are not yet available.
Build and inspect an agent-maintained Rust experiment around the `claw` CLI.
Project overview
Claw Code contains a Rust implementation of the `claw` terminal agent harness that can be built from source and used for diagnostics, one-shot prompts, and interactive sessions with an API key. The repository presents itself as an agent-planned and maintained museum exhibit, warns that the same-named crates.io package is the wrong install, and points practical users to LazyCodex or Gajae-Code.
Keeps coding agents iterating through role-based loops until the task is complete or the limit is reached.
Project overview
Ralph Orchestrator drives coding agents through role-based hats, events, and iterative loops until they emit LOOP_COMPLETE or reach the iteration limit. It supports backends such as Claude Code, Codex, Gemini CLI, Kiro, and OpenCode, with planning, persistent tasks and memory, plus gates for tests, lint, and type checks. Telegram can add human guidance, each MCP server is scoped to one workspace, and the web dashboard remains Alpha.
Coordinate AI coding agents with persistent git-backed work tracking
Project overview
Gas Town manages a workspace where multiple coding agents can work across projects without losing their state when sessions restart. Git-backed hooks, persistent identities, mailboxes, handoffs, and a Beads ledger keep work traceable, while project containers and worker roles organize parallel tasks.
Coordinate multiple coding agents across labeled tmux sessions
Project overview
NTM turns tmux into a local control plane for multi-agent development. It can spawn and label sessions, route work across panes, coordinate assignments and file reservations, protect risky operations with approvals, and preserve checkpoints and audit trails; robot JSON and local APIs make the same controls usable from scripts.
Manage coding-agent work through tasks, verification, and Git-visible change records.
Project overview
Agentplane adds an inspectable operational layer around local coding agents, recording task intent, plans, verification, context, and an Agent Change Record in repository artifacts. It supports fast work in the current checkout as well as per-task branches, worktrees, and PR handoffs for stricter review. It targets developers and teams that need reproducible agent work and requires Node.js 24+, Git, and a terminal.
Coordinate multiple coding CLIs in isolated tmux sessions
Project overview
CLI Agent Orchestrator places real coding CLIs in isolated tmux sessions and lets a supervisor delegate work through MCP. Workers can run in parallel, in sequence, or as a swarm, while the CLI, bundled web UI, and management server expose the same coordination model across providers.
Turn a software idea or existing codebase into an agent-driven improvement loop.
Project overview
Start with a rough software idea, refine it through a design conversation, and move into implementation, or point the tool at an existing project for repeated improvement cycles. It tracks experiments locally, evaluates each change before keeping or reverting it, and can run through Claude Code, Bob Shell, or OpenAI Codex.
Run parallel coding agents in isolated Git worktrees
Project overview
Emdash is a desktop environment for running coding agents in parallel, with each task isolated in its own Git worktree for reviewing diffs, CI checks, pull requests, and merges. It supports local projects and SSH/SFTP remote machines, and keeps app state in local SQLite. Emdash does not upload code or chats to its servers, but the selected agent CLIs may still send content to their own model providers.
Run a local Codex fork with browser tools and multiple agents
Project overview
Every Code is a community fork of OpenAI Codex for local terminal development. It extends the upstream tool with browser actions and multi-agent workflows, while Auto Drive and background Auto Review support longer execution and non-blocking checks. It supports ChatGPT sign-in or API-key use, can orchestrate external CLIs such as Claude and Gemini, and is not an official OpenAI product.
Run models and tools in a small, permission-aware terminal agent
Project overview
San is a native Go terminal harness distributed as a single binary of roughly 12 MB. It lets you switch models and search backends, attach plugins or MCP servers, and control actions through ask, auto-accept, or autopilot modes. Sessions can resume or fork, and a local inspector can replay transcripts; provider credentials are still required for the services you choose.
Explore an early supervision system for parallel coding-agent workflows.
Project overview
OpenAgents is developing Sarah as an inspectable supervision layer for bounded plans distributed across named Codex, Claude, and Grok accounts, using local desktops or optional cloud capacity. The repository is early and changing quickly, and Sarah does not yet compose the existing fleet components into the complete daily workflow. Its current milestone is to manage at least three useful work streams at once.
Agent harnessAI and agent developmentModel Context Protocol
deepagents
@langchain-ai·Python
Build extensible agents for long-running, multi-step work
Project overview
Deep Agents is an agent harness for long-running, multi-step work, with built-in planning, sub-agents, filesystem access, shell use, and persistence. Each part can be overridden or replaced without forking, and the framework can work with tool-calling frontier, open-weight, or local models.
Add modular agents, skills, rules, memory, and security hooks to coding assistants.
Project overview
ECC provides a modular environment of specialized subagents, development skills, rules, commands, session state, and security hooks for planning, testing, review, debugging, and reusable knowledge. It is primarily distributed as a Claude Code plugin, with adapters and configuration for Codex, OpenCode, Cursor, and other assistants. Its selective installer lets advanced users add only the components needed for their workflow rather than adopting the entire collection.
Build controllable AI agents in Python or TypeScript
Project overview
Strands Agents is a monorepo with Python and TypeScript SDKs for building model-driven agents. The SDKs support tools, MCP, streaming, multi-agent patterns, hooks, guardrails, context management, and multiple model providers, with examples for local development and deployment. Python requires 3.10 or newer and the TypeScript package requires Node.js 20 or newer; the default quickstart uses Amazon Bedrock credentials.