The spatial IDE for recursive multi-agent orchestration. It's like an Obsidian graph-view that you work directly inside of.

Real-time visualization of Claude Code agent orchestration — see your agents think, branch, and coordinate as they work.

Delegate tasks to DeepSeek right inside your Claude Code / Codex sessions.

Self-hosted agent OS with skills, workflows, MCP, and second brain storage.

Better subagent experience for Codex and Claude users

Awesome list for AI agent harness engineering: tools, patterns, evals, memory, MCP, permissions, observability, and orchestration.

Agor - team command center for all things agentic

Multi-agent research automation framework for LLM agents, with adversarial lab meetings, paper-review rounds, auditable Markdown workflows, an autonomous runtime watchdog, and a pixel-art web dashboard.

Manage and orchestrate your Claude Code, Codex, Cursor, Antigravity, Kimi, Grok, Devin, Droid sessions on your Machine. Spawn in parallel, ship in parallel. Open source.

Give AI agents ambitious work without losing the plot. nac is an open-source harness for long-running tasks, using a central orchestrator, threads, and structured episodes to stay aligned with your intent.

Open-source autoresearch powered by autonomous coding agents. Run Claude Code, OpenCode, and Codex with grading, shared knowledge, and multi-agent evolution. Accepted at COLM 2026.

Long-horizon agent skill for Claude Code / Cursor / Codex / Grok Build — multi-task ledger loop, host-portable, clean-context supervisor, verified gates. Markdown library (loop-graph), not a framework.