WaLiAPI

WaLiAPI 是一款本地运行的 LLM API 网关桌面软件(Tauri 2 + React + Rust)。支持各类 LLM 厂商渠道接入、Ollama 自部署模型、CPA 方式 ChatGPT 渠道接入,统一支持 Chat Completions / Responses / Anthropic Messages 三协议转换使用。内置安全审计引擎、知识库 RAG(HNSW + FTS5 混合检索)、Wiki 知识引擎和 MCP Server(29 个工具),配合 Codex、Claude Code、Gemini CLI 等 AI 编程工具使用。

fuzhengwei/WaLiAPI

View on GitHub ↗

WaLiAPI 是一款本地运行的 LLM API 网关桌面软件(Tauri 2 + React + Rust)。支持各类 LLM 厂商渠道接入、Ollama 自部署模型、CPA 方式 ChatGPT 渠道接入,统一支持 Chat Completions / Responses / Anthropic Messages 三协议转换使用。内置安全审计引擎、知识库 RAG(HNSW + FTS5 混合检索)、Wiki 知识引擎和 MCP Server(29 个工具),配合 Codex、Claude Code、Gemini CLI 等 AI 编程工具使用。

WaLiAPI grew +17.2% in the last 30 days, ranks 167th of 339 in LLM Gateway & Routing, last commit 30 days ago.

Star trajectory

82 days tracked
2026-08-31170 stars today2026-11-22
Momentum

+17.2% in 30d, above the LLM Gateway & Routing median of +1.5%.

Maintenance

Last commit 30 days ago, staler than the median of 5d.

How it compares in LLM Gateway & Routing

WaLiAPI
170
stars
+17.2% 30d
commit 30 days ago
LLM Gateway & Routing median
162
stars
+1.5% 30d
commit ~5d ago
Leader · OmniRoute
89.5k
stars
+11.9% 30d
commit today

Ranked 167th of 339 by stars.

Ranked by shared tags, then keywords, then stars
  1. Deploy a self-hosted AI stack with Docker Compose: local LLMs, chat, document parsing, embeddings…

    +11 (+6.5%) in 30d · Committed 4d ago · Shell · MIT

    Shares Local Runtime / Inference Engine, LLM Gateway & Routing, Memory & Knowledge (RAG)

  2. Your private, on-device personal AI assistant for macOS, Windows and Linux. Chat, create, search files, and…

    +24 (+18%) in 30d · Committed today · TypeScript · AGPL-3.0

    Shares Local Runtime / Inference Engine, LLM Gateway & Routing, Memory & Knowledge (RAG)

  3. ODS V3 Pre-Release: Public testing and refinement ahead of the official V3 launch. Turn your PC, Mac, or Linux…

    +235 (+3.1%) in 30d · Committed 2d ago · Python · Apache-2.0

    Shares Local Runtime / Inference Engine, Memory & Knowledge (RAG)

  4. NobodyWho is an inference engine that lets you run LLMs locally and efficiently on any device.

    +83 (+5.1%) in 30d · Committed 2d ago · Rust · EUPL-1.2

    Shares Local Runtime / Inference Engine, Memory & Knowledge (RAG)

  5. One-command installer for a self-hosted AI stack on your own server: n8n, Ollama, Open WebUI, OpenClaw, Dify…

    +12 (+1.3%) in 30d · Committed 25d ago · Shell · Apache-2.0

    Shares Local Runtime / Inference Engine, Memory & Knowledge (RAG)

  6. Streamline your workflow with Lynkr, a CLI tool that acts as an HTTP proxy for efficient code interactions…

    +4 (+0.6%) in 30d · Committed 7d ago · JavaScript · Apache-2.0

    Shares LLM Gateway & Routing, Local Runtime / Inference Engine

  7. A Docker-powered RAG system that understands the difference between code and prose. Ingest your codebase and…

    +0 (+0.0%) in 30d · Committed 252d ago · Python · Other license

    Shares Local Runtime / Inference Engine, Memory & Knowledge (RAG)

  8. 🥝 Self-hosted memory gateway for AI companions — OpenAI-compatible proxy with vector search, memory heat…

    +15 (+4.4%) in 30d · Committed 43d ago · Python · Other license

    Shares Memory & Knowledge (RAG), LLM Gateway & Routing

  9. 雨落下的地方,记忆会再次开花。可自部署的 AI 长期记忆与聊天网关。Self-hosted AI memory & chat gateway for long-term conversations.

    +56 (+28%) in 30d · Committed today · Python · MIT

    Shares Memory & Knowledge (RAG), LLM Gateway & Routing

  10. True on-device AI SDK for Kotlin Multiplatform (Android, iOS, Desktop, JVM, WASM). LLM inference…

    +20 (+9.7%) in 30d · Committed yesterday · Kotlin · Other license

    Shares Local Runtime / Inference Engine, Memory & Knowledge (RAG)

Language
Rust
License
MIT License
Contributors
19
Forks
56
Watchers
0
Open issues
17
Releases
36
Created
2026-07-17
Stars this week
+6

You've seen where WaLiAPI stands today.

Get the moves before everyone else: the 5 LLM Gateway & Routing repos climbing fastest, every Tuesday.

Free weekly digest. Double opt-in, unsubscribe anytime.

Maintain WaLiAPI?

Claim this page to add your own call-to-action.

Claim this page