impulse
Enables local execution of large language models to eliminate data privacy risks and cloud latency.
Impulse by Velocity: run AI models on your own computer, on Windows and Linux. Load any GGUF model and chat with web search, files, charts and voice, let it use your computer, and serve it to any app through an OpenAI-compatible API and MCP. Momentum memory up to 32M tokens. No cloud.
- Run large language models locally on Windows or Linux without using the cloud
- Serve an OpenAI-compatible API from your own computer to other applications
- Chat with local files, web search results, and data charts using GGUF models
Enables local execution of large language models to eliminate data privacy risks and cloud latency. The OpenAI-compatible API and MCP support allow teams to integrate private, high-context intelligence into existing development workflows without external dependencies.
Security-conscious engineering teams requiring private, local LLM execution with high-context memory and standard API compatibility.
https://github.com/Veloresearch/impulse
By Veloresearch
How to Get It
claude plugins install Veloresearch/impulse
Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.
Auto-generated from the tool's public listing — not hands-on verified. Cross-check against the source repo's README before running.
After installing, paste this into Claude:
Help me run large language models locally on Windows or Linux without using the cloud
Trust Signals Auto-scanned
Community Pulse Growing
Discussed on Hacker News
- TikTok has turned culture into a feedback loop of impulse and machine learning — Hacker News · 295 pts
- Impulse Tracker source code now available on GitHub — Hacker News · 200 pts
- Solar Impulse breaks solo record — Hacker News · 119 pts
3 mentions across 1 sources
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
Scored from trust signals (evidence-eval-v1): 35 GitHub stars; contributors unknown; last commit 0d ago; license no license.
Things to check
- Scanned, not hands-on tested — this entry was auto-scanned from public metadata (GitHub metrics, license, security flags). No reviewer has run it, and no tool-specific limitations have been documented yet.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.
Evaluation
Scored from trust signals (evidence-eval-v1): 35 GitHub stars; contributors unknown; last commit 0d ago; license no license.