Awesome Agent Orchestrators
Section: Multi-Agent Swarms · YAML-defined agent team with a lead agent that runs Claude Code and Codex together as one persistent system in tmux. npm CLI.
Entry
Appears in 4 awesome lists
by Mike Schwarz - Combines Claude Code, Codex, and Pi terminal sessions into persistent long-running teams. Agents message each other directly over tmux and queue work to each other, instead of the user relaying messages. Teams and agents are saved as YAML files, and a running team can be…
Section: Multi-Agent Swarms · YAML-defined agent team with a lead agent that runs Claude Code and Codex together as one persistent system in tmux. npm CLI.
Section: CLIs · Build your own network of agents from Claude Code, Codex and Pi: persistent teams with roles, shared context and owned work.
Section: Agent Orchestration · by Mike Schwarz - Combines Claude Code, Codex, and Pi terminal sessions into persistent long-running teams. Agents message each other directly over tmux and queue work to each other, instead of the user relaying messages. Teams and agents are saved as YAML files, and a running team can be…
Section: 4. Agentic AI & Multi-Agent Systems · Local multi-agent harness for defining persistent Claude Code and Codex teams, with YAML topologies, tmux sessions, durable state, and a shared terminal UI. Apache-2.0 licensed.
TypeScript-native agent framework (from the Gatsby team) with 22K+ stars and 300K+ weekly npm downloads. Connects to 40+ providers through one standard interface, with built-in workflows, RAG pipelines, and agent orchestration. The @mastra/deployer handles serverless deployment, and the eval…
Dual-layer harness orchestration: Crew handles autonomous agent delegation, Flow provides event-driven deterministic control (branching + shared Pydantic state). The clearest open-source example of mixing autonomous and scripted execution in the same harness.
🟢 — Local CLI and MCP toolkit for agent-assisted reverse engineering of native binaries, JavaScript/Electron and .NET applications, Android artifacts, firmware, and browser/process behavior, integrating analysis providers including Hopper, Ghidra, and IDA. — note: provider and host requirements…;…
Terminal-based AI coding agent with REPL mode for planning and executing complex tasks across multiple files, 2M token context.
A wonderful summary from Joshua Levy regarding command line (Bash in particular) tools, programs, tips, and tricks; contains many pointers to resources and repositories, in the form of "to do this you must know that", which gives great pointers but requires further investigation from different…
Lobe Chat is an open-source UI framework for building ChatGPT/LLM-based chat applications, featuring modern design, speech synthesis, multi-modal support, extensible plugins, and free one-click deployment for various AI agents github | website
Multi-provider AI agent framework that unifies 12+ LLM providers (OpenAI, Google, Anthropic, AWS, Azure, Groq, etc.) with workflow orchestration. Production-grade platform for building LLM applications with streaming, tool calling, caching, and enterprise features. Battle-tested at 15M+…
Free, local tool that tracks AI coding token usage and cost across 31 tools and agents by model, project, and task. Worth including because cross-tool cost visibility is the missing prerequisite for agent FinOps in multi-tool teams — most observability tools either require cloud upload or only…