AI tools built with Python

Dynamic continual learning model trained on 8GB VRAM

mini-AGI is a byte-level language model that trains from scratch on a single 8 GB VRAM GPU and keeps learning from a continuous stream of text. Weights live on disk and are paged onto the GPU as needed, so model size is bounded by disk spac

0 commentsY▲ 277 on HNLLMs & InfrastructureResearch & DataOpen Sourceby AI Launch Team

A universal – local-first SQLite memory engine for AI CLIs

Engrim is a local-first, project-scoped memory engine for AI coding agents, stored in a single SQLite file. It lets developers switch between tools like Claude Code, Cursor, Codex CLI, GitHub Copilot CLI, OpenCode and Google Antigravity on

0 commentsY▲ 93 on HNCoding & Dev ToolsAI AgentsOpen Sourceby AI Launch Team

Distill Jev into a local model – with a disagreement bound

Jevstiller distills a hosted Jev classifier into a local model, with a measured bound on how often the local model disagrees with Jev. It runs as a drop-in proxy, so batch jobs avoid a network call per answer while keeping answers close to

0 commentsY▲ 63 on HNLLMs & InfrastructureOpen Sourceby AI Launch Team

A research workspace where the agent can build its own panes

Masala, called Panel until September 2026, is a research workspace where an AI agent works beside you. Chat, files, PDFs and notebooks sit in one dock, and the agent can create custom viewers and apps when it needs them. It's an early build

0 commentsY▲ 54 on HNResearch & DataAI AgentsOpen Sourceby AI Launch Team

Replacing LLM judges with typed Jev decisions

jevals runs evals and guardrails for AI agents using Jev-style decision models instead of an LLM judge. All the checks for a trace, such as tool choice, groundedness, answer relevancy, prompt injection and PHI, go out as one request that co

0 commentsY▲ 47 on HNLLMs & InfrastructureAI AgentsOpen Sourceby AI Launch Team

A langgraph based workflow with a C++ CUDA harness to optimize CUDA kernels

An agentic CUDA kernel optimizer that turns workload descriptions into GPU implementations through a loop of code generation, correctness checks, benchmarking and refinement. A LangGraph agent explores kernel code and launch configurations,

0 commentsY▲ 37 on HNCoding & Dev ToolsAI AgentsOpen Sourceby AI Launch Team

High-Performance Serving Runtime for Robotics Models

InstinctFlash is a high-performance serving framework for robotics models from General Instinct (YC P26). It serves eight robotics model families, including pi05, LingBot-VLA, LingBot-VA and GR00T N1.7, through one runtime with Python and W

0 commentsY▲ 27 on HNLLMs & InfrastructureOpen Sourceby AI Launch Team