Niko1221/Strata
Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on localhost… Why it matters: useful plumbing for shipping LLM-powered features.
GitHub description: Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on localhost, optional image input.
Stars
23k
Last 24h
+1.2kest.
Last 7 days
+8.7kest.
Forks
2.3k
Who it's for
Owners of a gaming PC with an NVIDIA or AMD graphics card (12 GB VRAM or more) and 32 GB or more of RAM, running Windows or Linux, who want a large AI model running privately on their own machine and connected to their apps or coding agents.
- Private local chat and writing, with no data leaving the PC
- Connecting apps and coding agents to localhost via OpenAI- or Anthropic-compatible APIs
- Reading pictures and working through long documents or code
Star history (last 1 snapshot)
Only one snapshot so far. The chart fills in as OSS Radar collects daily snapshots.
* / est. Estimated: until we have enough daily snapshots for a repo, its gain is total stars ÷ days since creation. Measured numbers replace estimates automatically.
Maintainer? Add the badge to your README
Shows your live OSS Radar rank and links back here. Updates hourly.
[](https://ossradar.net/repo/Niko1221/Strata)<a href="https://ossradar.net/repo/Niko1221/Strata"><img src="https://ossradar.net/badge/Niko1221/Strata" alt="Trending on OSS Radar"></a>About Strata
Niko1221/Strata is a C++ project in the LLM tooling category, created 19 days ago. It has 23k GitHub stars and 2.3k forks, and gained +8.7k stars over the last 7 days (early estimate), ranking #2 of 167 LLM tooling repos tracked by OSS Radar this week.
See more trending LLM tooling repos or the top AI repos this week.
- Language
- C++
- Category
- LLM tooling
- Created
- Sep 24, 2026
- Last push
- Oct 12, 2026
Similar rising repos
- DietrichGebert/ponytail+9.2kest.
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote. Why it matters: useful plumbing for shipping LLM-powered features.
- affaan-m/ECC+7.3kest.
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex… Why it matters: useful plumbing for shipping LLM-powered features.
在 dsh 里装上这个插件即可,无需登录、注册或填 API Key,就能使用包括 DeepSeek V4.1 Flash、Kimi K3 在内的前沿模型——完全免费,不限量。 All you do is install this plugin in dsh: no login, no… Why it matters: useful plumbing for shipping LLM-powered features.
- Graphify-Labs/graphify+4.6kest.
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex… Why it matters: useful plumbing for shipping LLM-powered features.
- JuliusBrussee/caveman+4.1kest.
why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman. Why it matters: useful plumbing for shipping LLM-powered features.
- NousResearch/hermes-agent+4kest.
The agent that grows with you. Why it matters: useful plumbing for shipping LLM-powered features.