Cross-vendor model router
Routes across Claude/GPT/Gemini/Qwen for cost arbitrage + security defense-in-depth.
3 primary frameworks · 17 lower-confidence entries
JavaScript-DSL workflow orchestration engine that captures repeatable AI coding agent workflows with tracks, condition groups, and long-running persistence…
Tauri desktop app providing visual control plane, task scheduler, git worktree manager, and headless REST API for Codex CLI + Claude Code sessions.
Kanban TUI for AI coding agents with a structurally enforced human review gate (REVIEW → DONE cannot be automated) — one git worktree per task, 14 agent…
Show 17 lower-confidence entriestier-b · tier-c · unknown · delta reports
These entries map to § a16 by tag but carry weaker evidence — fewer documented primitives, delta reports of absent skills, or marketing-only sites without a public repo. They're listed for completeness; treat them with appropriate caution.
Zero-learning-curve teams-first multi-agent orchestration for Claude Code with autopilot (6-phase lifecycle), ralph (PRD-driven persistence), ralplan (3-stage c…
Multi-provider AI coding agent orchestration daemon with cross-device access (phone/desktop/CLI) and git worktree isolation.
Routes Claude + Codex + Gemini to task-appropriate collaboration strategies (direct-fix through full-collaborate) with hook-based per-turn state tracking that s…
Routes Claude Code tasks to the optimal AI agent (Codex, Factory Droid, Ollama, Claude) based on configurable cost/capability profiles, with OAuth account pool …
Multi-agent orchestration testbed: each agent in own container + git worktree, harness-agnostic (Claude/Gemini/Codex/OpenCode), OTEL telemetry, emergent coordin…
Provide a multi-model Claude Code setup routed through LiteLLM + GitHub Copilot, with skills for deep research, cross-tool delegation, and code workflows.
Route every task to the cheapest capable model while enforcing TDD, ADR compliance, iCPG intent tracking, and Telos intent fidelity — making token economics a f…
Bridges any coding agent (Claude Code, Cursor, Codex, OpenCode) to IM channels and HTTP APIs, giving agents external reach without framework lock-in.
29 production-tested, hyper-specific domain-specialist droids for a Cloudflare Workers/Neon/tRPC stack, with forced context injection replacing codebase explora…
Orchestrate heterogeneous AI agent teams via visual kanban drag-and-drop, routing tasks by complexity to the right model without writing prompts.
Two-layer network-isolated local sandbox (mitmproxy allowlist + iptables firewall) for running AI coding agents with minimal filesystem access and proxy-injecte…
Structured 11-skill development pipeline (design→review→implement→review→test→doc) with persistent Capy BM25 knowledge base, language-specific profiles for 8 la…
Provides a specialist AI agent runtime with tap-registry community agents, per-role multi-model routing, hard cost enforcement, and policy-as-code guardrails — …
Routes code and plan review through a 3-model council (GPT/Gemini/Grok) to catch what any single model misses via multi-model consensus.
Passive session observability (FTS5 dashboard over JSONL) + inter-LLM delegation (Claude calling Qwen as a cheaper advisory model)
Automate Director+Worker AI development by keeping the Director context-thin and giving each phase Worker a fresh session with only relevant context.
Enforce a gated spec-driven AI development workflow with human approval at planning and PR stages, multi-model review, and full auditability via event logs.