whereismyai
Strim Engine
Strim Engine is a local model server and agent harness running Qwen3.8-27B on Apple Silicon.
Strim Engine is a local model server built for coding agents to run Qwen3.8-27B on Apple Silicon. It operates as a single Swift binary with a menu-bar app, ensuring data stays on your Mac. The software is designed to integrate with tools like Claude Code and Codex. It provides live capture capabilities and optimized performance metrics for decode tasks and shared prefixes. The project is open source under the MIT license.
Strim Engine at a glance
Key features
- Local model server for coding agents
- Single Swift binary execution
- Menu-bar app interface
- Integration with Claude Code and Codex
- Optimized for Apple Silicon
- MIT licensed open source code
Use it for
- Run local models for coding agents
- Execute local inference on Apple Silicon
- Host Qwen models securely on Mac
Alternatives to Strim Engine
- Strata — Runs large AI models locally on consumer gaming PCs without server reliance.
- MTPLX — It runs local models twice as fast via native MTP speculative decoding.
- jevgrep — Reduces coding agent costs by providing targeted, relevant repository context.
- Stroq — Scans recorded sessions and guards future actions with local hooks.
- Kapitsa — Optimized inference engine delivering high token generation speeds on Apple Silicon.
- mini-SWE-agent — It offers high performance with a simplified, minimal codebase.
- ZCode — Integrates GLM-5.3 with multi-agent workflows and remote chat control.
- Gtree — Runs multiple AI coding agents together and flags file overlaps.
- Pulsar — It is the fastest inference engine for Qwen models on Apple Silicon.
- Qwen Code — Fully open-source framework and models with multi-protocol support.
- ModLens — Converts screenshots and charts into structured JSON data for coding agents.
- claude-mem — It shares persistent, searchable agent memory across sessions and devices.
All Strim Engine alternatives