Automatic LLM router — 82% cost savings, 79.4% accuracy, 93.4% pass rate. Drop-in OpenAI proxy.
-
Updated
May 12, 2026 - Python
#
model-routing
Here are 274 public repositories matching this topic...
Open-source LLM router & AI cost optimizer. Routes simple prompts to cheap/local models, complex ones to premium — automatically. Drop-in OpenAI-compatible proxy for Claude Code, Codex, Cursor, OpenClaw. Saves 40-70% on AI API costs. Self-hosted, no middleman.
python ai proxy self-hosted gemini openai codex cost-optimization llm openai-proxy ollama llm-proxy llm-router llm-gateway claude-code ai-cost-reduction model-routing ai-router prompt-routing openclaw
-
Updated
Jun 8, 2026 - Python
The local firewall for AI agents — keep your secrets off the model, the API relay, and the supply chain. Local credential masking, per-route model routing, and security detectors on the wire. Free & fully open source.
mcp guardrails local-first supply-chain-security llm-proxy llm-firewall llm-gateway claude-code ai-agent-security model-routing secret-redaction indirect-prompt-injection agent-firewall zero-trust-firewall credential-masking
-
Updated
Jun 11, 2026 - TypeScript
Private AI assistant, AI agent, and unified model proxy for Claude Code, Codex CLI, Gemini CLI & OpenClaw. Skills, MCP, tools, channels, tasks,model routing, accounts, keys, logs, dashboard.
api-gateway proxy-server openai developer-tools api-proxy claude multi-account coding-assistant agent-framework chatgpt anthropic free-ai agentic-ai ai-proxy agent-skills claude-code codex-cli model-routing openclaw openclaw-extension
-
Updated
Jun 11, 2026 - JavaScript
Route inference across providers.
golang api-gateway inference openai multi-model observability load-balancing model-serving llm anthropic llm-proxy cost-tracking ai-gateway llm-router ai-infrastructure token-tracking model-routing inference-routing mist-stack provider-abstraction
-
Updated
Feb 17, 2026 - Go
OpenVitamin is a local-first AI execution platform that unifies Agents, Workflows, and multi-model inference into a single programmable system — designed for building real, production-grade AI applications.
agent workflow ai multi-model execution-engine ai-agents rag fastapi ai-platform local-first onnxruntime llm llama-cpp local-ai ai-platforms agent-orchestration openai-compatible agent-runtime model-routing
-
Updated
May 15, 2026 - Python
Free, self-hosted AI model router. OpenRouter / ClawRouter alternative using your own API keys. 14-dimension classifier routes to the right model (Anthropic/OpenAI/Kimi) automatically. No middleman, no markup. Built for OpenClaw.
self-hosted openai cost-optimization anthropic llm-proxy llm-router ai-proxy model-routing openclaw openrouter-alternative ai-model-router
-
Updated
Feb 14, 2026 - TypeScript
FreeUltraCode - Free LLM channel router for Claude Code, Codex, Gemini, and local models.
gemini multi-model codex tauri local-first coding-assistant ai-chat llm free-ai free-llm claude-code model-routing free-models
-
Updated
Jun 10, 2026 - TypeScript
The Python Harness for Production AI Multi-Agent Systems
budgeting multi-agent memory-management observability harness multi-agent-systems rag multimodal-agent agentic-rag context-engineering model-routing harness-engineering
-
Updated
May 18, 2026 - Python
🏆Winning Project | ModelGate is a contract-aware AI control plane that ingests customer contracts, extracts SLA/privacy/routing constraints, and generates an OpenAI-compatible endpoint that automatically routes every request to the optimal model. Simple queries go to cheap models. Complex queries go to premium ones.
reinforcement-learning ai hackathon model nextjs routing openai lora quantization cost-optimization fine-tuning fastapi openai-api llm llamacpp gguf grpo openai-compatible model-routing
-
Updated
Mar 22, 2026 - TypeScript
Claude Code hooks that auto-switch model tier based on task complexity
shell bash automation oss developer-tools opus haiku claude sonnet ai-tools llm anthropic llm-router claude-code claude-hooks claudecode-hooks model-router model-routing claude-code-plugin prompt-classification
-
Updated
Mar 13, 2026 - Python
Stateless LLM runtime that dynamically routes, loads, executes, and unloads models per request with bounded VRAM caching and intelligent model selection.
systems-programming llm generative-ai ai-infrastructure latency-optimization model-routing vram-optimization model-scheduling
-
Updated
Apr 12, 2026 - Rust
Intelligent model orchestration for Claude Code - routes queries to optimal Claude model (Haiku/Sonnet/Opus) based on complexity. It also includes many more features. If this project is working well for you and would like to support me, just help spread the word. Thanks!
-
Updated
Jan 26, 2026 - Python
Auto-delegation, status truth, and cost-aware model routing for OpenClaw agents
slack automation typescript ai-agents feishu llmops agent-orchestration subagents model-routing openclaw
-
Updated
Jun 6, 2026 - TypeScript
Multi-Model Collaboration Pipeline — orchestrate AI models as a DAG. RL routing, multi-verifier voting, agent mesh, self-improving. Works with OpenAI, Anthropic, Gemini, DeepSeek. npm install mmcp-core | pip install mmcp-core
python cli typescript sdk reinforcement-learning ai mcp orchestration multi-agent gemini openai multi-model dag ai-agents llm anthropic agent-coordination deepseek context-protocol model-routing
-
Updated
Jun 3, 2026 - TypeScript
Stop overpaying to run your agents. Kalibr routes every request to lower-cost model and tool paths without degrading performance.
python openai thompson-sampling ai-agents production-ai ai-sdk adaptive-routing cost-reduction langchain anthropic crewai ai-infrastructure llm-cost multimodal-ai llm-routing agent-reliability model-routing inference-cost execution-path-routing agent-cost-optimization
-
Updated
Jun 3, 2026 - Python
Scalable LLM cost enforcement middleware for Node.js with budget protection and multi-provider support
nodejs middleware typescript gemini openai budget cost-control llm anthropic token-counter model-routing automatic-failover ai-cost-management gssoc26
-
Updated
May 27, 2026 - TypeScript
Claw is a local-first AI control plane that runs powerful open models on your machine and connects to top LLM providers. It intelligently routes every prompt to the best model, giving you one secure workspace for chat, memory, context, connectors, routing, and full AI orchestration.
open-source machine-learning ai artificial-intelligence openai multi-model gpt ai-agents llm prompt-engineering llmops anthropic anthropic-claude local-llm agentic-ai ai-orchestration ai-agents-automation claude-code model-routing opus-4-7
-
Updated
Jun 8, 2026 - TypeScript
Ultra-low-latency LLM gateway with microsecond caching, dynamic routing, budgets, analytics, and forecasting.
redis distributed-systems api-gateway rate-limiting low-latency observability cost-optimization multi-provider vector-search pii-redaction qdrant llmops llm-proxy ai-gateway ai-infrastructure llm-gateway llm-routing openai-compatible semantic-caching model-routing
-
Updated
Apr 2, 2026 - Go
Intelligent model routing for OpenClaw - Sonnet 4.6 vs Opus 4.6 based on task complexity
-
Updated
Feb 18, 2026
Improve this page
Add a description, image, and links to the model-routing topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the model-routing topic, visit your repo's landing page and select "manage topics."