자체 호스팅 AI 에이전트 게이트웨이는 Go. Single binary, low memory로 작성되어 자체 기계에 완전히 실행됩니다.

Felix는 LLMs — Claude, GPT, Gemini, Qwen, Ollama 또는 OpenAI 호환 엔드포인트로 연결하고 에이전트가 원격 MCP 서버의 고정 레지스트리를 사용하여 하드웨어에서 작업을 수행 할 수 있습니다.

디자인 철학

1. **자가 충분합니다. ** 하나의 바이너리, 상태의 하나의 디렉토리, 필요 네트워크 의존성. LLM은 현지일 수 있습니다. 벡터 인덱스는 in-process입니다. 지식 그래프는 SQLite 파일입니다. Felix 클라우드는 없습니다, Felix 계정 없음, 누구가 꺼질 수 있는지 Felix 백엔드.
2. ** 튼튼한. ** Long-running 에이전트 터치 파일, 쉘 아웃, flaky API에 대화, 그리고 재시작을 통해 상태를 축적. 모든 외부 통화에는 타임아웃이 있습니다. 모든 큐에는 모자가 있습니다. 각 per-call 자원에는 쌍꺼풀이 있습니다. On-disk 상태는 다음 부하에 그립니다.
3. ** 비 기술적인 사람들로 상자에서 사용 가능. ** 기본 설치 - 구성 편집 없음, API 키 없음, vim - 그냥 작동해야합니다. 고급 구성은 복잡 할 수 있지만 기본 경로의 방법으로는 안됩니다.
4. **기본값으로 저장합니다.

Felix

A self-hosted AI agent gateway written in Go. Single binary, low memory, runs entirely on your own machine.

Felix connects you (via CLI or web chat) to LLMs — Claude, GPT, Gemini, Qwen, Ollama, or any OpenAI-compatible endpoint — and lets agents execute tasks on your hardware using a fixed registry of in-process tools plus any number of remote MCP servers.

Design philosophy

1. Self-sufficient. One binary, one directory of state, no required network dependency. The LLM can be local. The vector index is in-process. The knowledge graph is a SQLite file. There is no Felix cloud, no Felix account, no Felix backend that anyone could turn off.
2. Robust. Long-running agents touch files, shell out, talk to flaky APIs, and accumulate state across restarts. Every external call has a timeout. Every queue has a cap. Every per-call resource has a paired cleanup. On-disk state heals itself on the next load.
3. Usable out of the box by non-technical people. The default install — no config edits, no API keys, no vim — must just work. Advanced configuration can be as complex as it needs to be, but it must not be in the way of the default path.
4. Secure by default. An agent that can read files, run shell commands, and make web requests is genuinely powerful — defaults have to protect users who won’t read the security docs. Felix binds to localhost only, ships the bash tool in allowlist mode rather than full shell access, blocks web requests to internal IP ranges and cloud metadata endpoints, contains file access to each agent’s workspace with symlink resolution, and writes config and session files with owner-only permissions. You can relax any of it deliberately; you don’t have to opt out of it.

Features

Interfaces

• Single binary, no runtime dependencies. Download and run.
• macOS / Windows system tray app that runs the gateway in the background and serves a web chat at http://127.0.0.1:18789/chat.
• felix chat CLI that auto-detects a running gateway and shares its session, memory, and MCP state — start in the browser, continue in the terminal.
• WebSocket JSON-RPC 2.0 control plane for programmatic access.

Models

• Claude, GPT, Gemini, Qwen, Ollama, LM Studio, DeepSeek, or any OpenAI-compatible API.
• Bundled Ollama runtime so you can run agents with no API key. Downloads gemma4 on first startup if no other models are available.
• Per-agent extended reasoning (off|low|medium|high) mapped to Claude thinking budgets, OpenAI reasoning_effort, Gemini ThinkingConfig, and Qwen enable_thinking.
• Context-window auto-detection from the model identifier (handles proxy prefixes correctly), with a per-agent contextWindow override for unusual fine-tunes.
• Cross-provider tool portability: JSON Schema fields one provider rejects (Gemini drops anyOf/oneOf/format; OpenAI drops $ref/definitions) are stripped at the provider boundary.

Memory & knowledge