crp4222/PrivAiTeSelf-hosted PII redaction proxy for LLM APIs and agent CLIs. Scrubs names, emails and secrets from Claude Code, Codex and any OpenAI-compatible app before requests leave your machine, tool-call arguments included, then restores them in the reply. Local detection, zero telemetry.
Python★ 38Sep 11, 2026
PyPI · npm75Goodhealth index
domondi1/inferrailSelf-hosted OpenAI/Anthropic-compatible gateway: give each AI agent run a dollar budget, enforced before the provider, with a payload-free per-run cost record.
Python★ 0↓ 4,824/moOct 5, 2026
openziti/llm-gatewayZero trust LLM gateway. OpenAI-compatible proxy with semantic routing and load balancing across OpenAI, Anthropic, Ollama, vLLM, and any compatible backend. Identity-based access, virtual API keys, and end-to-end encryption via OpenZiti
Go★ 95Sep 19, 2026
sinameraji/kimiflareMoonshot kimi k3 terminal based coding agent & harness running on your own Cloudflare account.
TypeScript★ 172↓ 5,789/moSep 12, 2026
sozercan/vekil🧑💼 AI gateway exposing Anthropic, Gemini, and OpenAI-compatible APIs, backed by GitHub Copilot, OpenAI Codex, Microsoft Foundry, and compatible model servers
Go★ 18Sep 10, 2026
Go · npm69Goodhealth index
OpenCSGs/csgliteCSGLite is a lightweight local LLM inference platform. One command downloads, loads, and chats with models. It ships a web UI, OpenAI-compatible API, llama.cpp inference, resumable downloads, marketplace browsing, and one-click AI app and coding-agent setup—all in a single cross-platform binary.
Go · TypeScript★ 49Oct 20, 2026
Go · PyPI69Goodhealth index
Go★ 38Sep 10, 2026
hishamkaram/claude-code-routerA local gateway that routes Claude Code sessions to OpenAI-compatible and Anthropic-compatible models, with same-session switching and visible compatibility behavior.
Go★ 4Sep 10, 2026
PyPI · npm65Goodhealth index
manojmallick/gavioThe open standard AI gateway — PII protection, audit, reliability & cost control as composable interceptors. Same API in Python, Java & JavaScript.
Java · Python · TypeScript★ 5↓ 265/moSep 11, 2026
PyPI · crates.io · npm63Moderatehealth index
anvai-labs/sandhiSandhi — the metering layer for AI agents. An open-source AI usage gateway: meter, attribute, and budget every model call across shared keys.
Rust · Python★ 0↓ 18.9K/moSep 15, 2026
Go · npm63Moderatehealth index
liulixin-lex/xy-apiA unified AI model hub for aggregation & distribution. It supports cross-converting various LLMs into OpenAI-compatible, Claude-compatible, or Gemini-compatible formats. A centralized gateway for personal and enterprise model management. 🍥
Go★ 1Sep 13, 2026
npm62Moderatehealth index
SeanHogg/Builderforce.aiAgentic AI Coding Platform that enables everyone to train, design and embed custom LLMs into a custom agent. Deploy your agent into the builderforce (a workforce and hiring platform). Explore skills, personnas, content, governance and workforce agents in the marketplace.
TypeScript★ 5↓ 6,265/moSep 10, 2026
npm62Moderatehealth index
Go · TypeScript · JavaScript★ 36↓ 23.8K/moSep 5, 2026
Go · npm59Moderatehealth index
xraph/nexusComposable AI gateway library for Go. Route, cache, guard, and observe LLM traffic at scale.
Go★ 0Sep 19, 2026
PyPI54Moderatehealth index
Akunimal/AI-Router-Blocker-AiOOpen-source DevSecOps gateway for AI traffic. Intercept, audit, and route LLM requests to prevent data leaks and enforce zero-trust security policies.
Python★ 1Jul 26, 2026
Go · npm53Moderatehealth index
Go · TypeScript★ 3Sep 27, 2026
PyPI51Moderatehealth index
BlockRunAI/blockrun-litellmLiteLLM adapter for BlockRun — call x402-paid AI models through LiteLLM (custom provider or local OpenAI-compatible proxy)
Python★ 0↓ 347/moSep 13, 2026
npm51Moderatehealth index
Continuum-AI-Corp/orcarouter-mcp-serverOfficial MCP server for OrcaRouter — the LLM gateway with auto-routing and fallback chains. Browse models and chat from Claude Desktop, Cursor, Windsurf, or any MCP client.
TypeScript★ 12↓ 507/moSep 13, 2026
npm51Moderatehealth index
mpointer/llm-governance-gatewayThe governance layer LLM proxies promised as a TypeScript library you can read. Every call runs through one governed pipeline: rate limit → spend caps (per-user + global circuit breaker) → cache → schema-validated provider failover → usage log → LLM-judge No sidecar proxy to deploy.
TypeScript★ 2↓ 3,412/moAug 25, 2026
Go · npm51Moderatehealth index
Go · Svelte★ 103Sep 12, 2026
npm50Moderatehealth index
TypeScript★ 0↓ 1,888/moSep 18, 2026
PunkTechnologies/punk-sdkPublic TypeScript SDK and integration examples for Punk, the adaptive runtime for production AI agents.
TypeScript★ 1↓ 422/moOct 21, 2026
Go · npm48Weakhealth index
napmany/llmsnapFast LLM swapping with sleep/wake support, compatible with vllm, llama.cpp, etc. llama-swap fork.
Go · Svelte★ 56Sep 24, 2026
Go · npm48Weakhealth index
Go · Svelte★ 0Sep 17, 2026
xk1ko/aiglooSelf-hosted AI gateway. Route, translate and track requests across providers, with access keys, budgets, and a built-in dashboard.
TypeScript★ 6↓ 110/moSep 13, 2026
flowork-os/flowork_routerNever hit a rate-limit again. Route Claude Code, Cursor & 40+ providers through the subscription you already pay for, cut 40-80% tokens (RTK), stay un-banned. Self-hosted LiteLLM / OpenRouter / 9router alternative — one Go binary, anti-ban + sovereign P2P mesh.
Go★ 7Jul 15, 2026
Go · npm44Weakhealth index
aurorallm/auroraThe Fastest enterprise AI gateway — route LLM traffic across OpenAI, Anthropic, Gemini, Groq & 30+ providers via a single API. Self-hosted, no vendor lock-in. ( 55x faster than litellm )
Go · TypeScript★ 38Sep 11, 2026
tokenpartyhub/TokenPartySelf-hosted AI gateway — route, observe, and control your LLM API traffic. OpenAI ↔ Anthropic protocol translation, cost-based smart routing, per-user budgets, built-in dashboard. Zero dependencies.
TypeScript★ 1↓ 249/moSep 12, 2026
jasminnanda/kirogo⚡ Turn your Kiro subscription (Amazon Q Developer / AWS CodeWhisperer) into OpenAI- and Anthropic-compatible APIs. Use Claude, GPT, Qwen and GLM models from Cursor, Claude Code, Cline, Zed and Aider. One static Go binary, zero dependencies.
Go★ 1Sep 19, 2026
Go · npm · Packagist +138Weakhealth index
Astrenix/nexcore-sdkOfficial Tovanix platform SDKs (formerly NexCore) — multi-chain payments & payouts / exchange rates / TRON energy / SMTP / account / virtual cards. PHP · Python · Node.js · Go, 7 namespaces, 44 endpoints.
PHP · Python · Go★ 0Sep 14, 2026