PicoLM v1.0-rc2 (“Yura Kana”). Run an LLM on Digital Unix

PicoLM v1.0-rc2 ("Yura Kana"). Run an LLM on Digital Unix is an AI tool for code workflows, especially add memory to ai agents and manage agent context. Cross-platform pure C+GPU inference for Llama 2-family, Mistral Nemo, GPT-2, Gemma-3n, and Qwen 3.x SSM GGUF files. Enhancements over parent repo are 99% coded by Qwen 3.6-27b with my own lightweight custom agentic Pythonshit. No NodeJS cancer has been installed during the development. 0 money spent on cloudslop. Contains 0% ngxson - whoreson/picolm. Verified public information highlights picoLM is an LLM inference engine written in C99, it currently supports llama-2, GPT-2, Qwen 3, 8(+MoE) and Gemma-3n models, significant amount of work went into CPU SIMD acceleration/testing/correctness. In AI Finderz, the strongest matching use cases are add memory to ai agents, manage agent context, connect mcp tools, build ai agents. The project is publicly presented as open source. The public project is open source. Check the official page for hosted services, support or usage-specific costs. AI Finderz checked the public source on 2026-09-23 and uses the official page as the factual basis for this profile.