Keyword: model-routing
- agentic-flowReleased4d agoVersion2.1.0
The agentic meta-harness — freeze the model, evolve the harness. An open runtime that routes each query to the cost-optimal model, evolves its own harness (planner/context/reviewer/retry/tool/memory/score policy) and autonomously repairs code, then orches
- adaptive-memory-multi-model-routerReleased14h agoVersion2.14.60
RouterArena #1 among known public baselines: 96.77% accuracy, $0.0768/1K, 1.0000 robustness. OpenAI-compatible LLM router across 47+ providers.
- vibeostheogReleased13h agoVersion0.25.55
Cost-aware delegation enforcer for OpenCode. Tracks model usage, routes Task subagents to cheaper tiers, surfaces cumulative savings in chat. Includes research audit, reporting framework, project memory, progressive scratchpad decadence, and trinity CLI f
- local-model-suitability-mcpReleased7h agoVersion1.1.28
AI model router for agents. Checks whether a local model can handle the task before calling cloud inference. LOCAL/CLOUD verdict saves cost on every call.
- cligateReleased6d agoVersion1.4.1
Local AI control plane with a resident private assistant for task execution and a unified model proxy API for Claude Code, Codex CLI, Gemini CLI, OpenClaw, accounts, API keys, logs, and usage.
- tryaiiReleased12h agoVersion0.4.0
AI model router for Node.js and TypeScript with benchmark, cost, and speed-based ranking
- cascadeflow-core-smrReleasedyesterdayVersion1.1.1-smr.1
cascadeflow TypeScript library - Smart AI model cascading for cost optimization
- margiqReleased2d agoVersion0.1.3
Workflow-aware model routing that cuts LLM waste safely
- zerogpu-openclaw-pluginReleased3d agoVersion0.1.10
ZeroGPU Router plugin for OpenClaw: route trivial AI tasks (summarize, classify, redact PII, extract JSON, follow-ups) to small/nano models via MCP. Cuts agent inference costs without changing your reasoning model.
- @gfrmin/credence-openclawReleased3d agoVersion0.2.0
Bayesian routing and governance for OpenClaw — picks the right model per turn (before_model_resolve) and blocks low-EU tool calls (before_tool_call). One brain, one utility function, your cost/quality trade-off. Requires the credence-governor daemon on :8
- @wzrd_sol/ai-providerReleased4d agoVersion0.1.0
Vercel AI SDK provider that routes inference through WZRD's velocity oracle.
- hyper-agent-skillsReleased4d agoVersion0.1.6
Hyper Skills for cross-agent watching, cost-aware model routing, visual planning, codebase mapping, and token-saving replies.
- modelis-openaiReleased6d agoVersion0.1.0
Drop-in OpenAI-compatible local proxy for the Modelis Auto Chat API on RapidAPI. Use Modelis in Aider, Cline, Continue, or any OpenAI SDK with one base_url.
- clavueReleased1h agoVersion9.11.5
Clavue: execution-first AI coding CLI with direct repo tools, provider routing, native workflows, MCP integration, and long-session recovery