Run Agent Skills with mistral.rs v0.8.10: /v1/skills support and more
Details
- External ID
- 48581792
- Source
- HN
- Company
- —
- Product
- —
- Website domain
- —
- Launched
- June 18, 2026
- Cohort
- —
- Upvotes
- 20
- Upvotes percentile
- 0.7472677595628415
- Tags
- —
- Fetched at
- Sept. 7, 2026, 9:26 p.m.
- Updated at
- Sept. 7, 2026, 9:26 p.m.
Description
Hey all! I'm the maintainer of mistral.rs. I just landed support for OpenAI-compatible Agent Skills via a /v1/skills endpoint, and it works with local open models.Until now Skills have basically been locked to closed models, and with the ability to have private, local intelligence becoming increasingly important, but this feature allows you to do XYZ with local models.It's fully compatible with OpenAI's /v1/skills API, so you can drop mistral.rs into your existing code with minimal difficulty.We support the accompanying tools too: /v1/files or input_file for attaching files to your prompts, and mistral.rs also allows models to send generated files back using the OpenAI-compatible method.It's also easier than ever to try mistral.rs: we are including prebuilt binaries for NVIDIA CUDA, Apple Silicon, and CPU! # Linux/Mac > curl --proto '=https' --tlsv1.2 -sSf https://raw.githubusercontent.com/EricLBuehler/mistral.rs/ma... | sh # Windows > irm https://raw.githubusercontent.com/EricLBuehler/mistral.rs/ma... | iexThen: mistralrs serve --agent --isq 4 -m google/gemma-4-E4B-itSuper excited for you to try this out and any feedback! Do you have any suggestions for what you would like to see in the next releases?Check out the GitHub: https://github.com/EricLBuehler/mistral.rs Docs & Quickstart: https://ericlbuehler.github.io/mistral.rs/
Enrichment
- Theme
- developer tools for AI agents
- Vertical
- Horizontal
- Function
- Model & infra
- Audience
- Developer
- AI stance
- AI-native
- Project type
- Hobby / open-source project
- Normalized one-liner
- mistral.rs runtime with agent skills support
- Manually corrected
- False
Could you build this?
No Extending mistral.rs with agent skills involves low-level systems programming in Rust and deep familiarity with local LLM inference engines and GPU/quantization kernels.
What it would actually take: This requires modifying high-performance Rust inference engines (such as Candle-based architectures), implementing custom execution pipelines for OpenAI tool/skill calling schemas, and handling token streaming states efficiently under heavy memory constraints. It demands specialized systems engineering and machine learning runtime expertise.
Discussion
2 comments analyzed.
Concerns raised: Unclear what 'skills locked to closed models' means for markdown prompts
Feature requests: OpenAI compatibility as standard interface for local model tooling
Competitors
Other products that read as similar to this one — 124 launches clear the similarity bar, closest 8 shown.
Attention rank: #36 of 125 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 203 days after the earliest competitor.
- Mistle · hn · 2026-05-13 · 6 upvotes · similarity 0.48
- Distributing AI agent skills via NPM · hn · 2026-01-09 · 6 upvotes · similarity 0.45
- Running local OpenClaw together with remote agents in an open network · hn · 2026-04-04 · 8 upvotes · similarity 0.41
- Running AI agents across environments needs a proper solution · hn · 2026-03-24 · 8 upvotes · similarity 0.41
- Skillscript · hn · 2026-07-12 · 18 upvotes · similarity 0.40
- SkillRegistry · ph · 2026-09-21 · 2 upvotes · similarity 0.39
- SkillGrill · ph · 2026-09-22 · 2 upvotes · similarity 0.39
- OneCLI · hn · 2026-03-12 · 161 upvotes · similarity 0.39
Other launches for this product
- No other launches for this product.
Same idea, different domain
Nobody's really built a model & infra tool for Fintech yet.