{"owner":"RightNow-AI","github":"https://github.com/RightNow-AI","claimed":false,"inventory":[],"indexed":[{"repo":"RightNow-AI/openfang","github":"https://github.com/RightNow-AI/openfang","description":"Open-source Agent Operating System","language":"Rust","stars":18119,"topics":["agent-framework","ai-agents","llm","mcp","open-source","openclaw","operating-system","rust"],"license":"Apache-2.0","category":"ai-agents"},{"repo":"RightNow-AI/picolm","github":"https://github.com/RightNow-AI/picolm","description":"Run a 1-billion parameter LLM on a $10 board with 256MB RAM","language":"C","stars":1908,"topics":["arm","embedded","inference","llm","openclaw","picoclaw","quantization","raspberry-pi","risc-v"],"license":"MIT","category":"ai-agents"},{"repo":"RightNow-AI/rightnow-cli","github":"https://github.com/RightNow-AI/rightnow-cli","description":"Claude Code for CUDA. Free AI assistant that actually understands GPU architecture","language":"Python","stars":111,"topics":["cli","cuda","gpu"],"license":null,"category":"cli-tools"},{"repo":"RightNow-AI/local-kimi","github":"https://github.com/RightNow-AI/local-kimi","description":"Optimized local serving engine for Kimi-Linear-48B: INT4 quantizer, fused decode kernels for a measured 3.18x, and an OpenAI-compatible server. Ships with k3, a bridge that detects the client per request so Claude Code, Codex, Cline, Aider and opencode all work unchanged.","language":"Python","stars":37,"topics":["anthropic-api","claude-code","coding-agents","int4","kimi","llama-cpp","llm-inference","local-llm","openai-api","quantization"],"license":"Apache-2.0","category":"mcp-servers"}],"how_to_buy":"GET /r/RightNow-AI/<repo> (Accept: application/json) for any listed repo here: tree, README, price and the checkout to pay (x402; rehearse first at its test twin, simulated money). Repos under 'indexed' are free: clone them from GitHub."}