AI & ML

Models, agents, inference engines, training and evaluation code.

12 projects

AI & ML

OpenBot gives every AI coworker its own browser and an audit trail

CopilotKit/OpenBot

CopilotKit's self-hosted template runs each agent in its own container behind a policy gateway. Out of the box, that policy allows everything.

★ 5.6K · TypeScript · September 28, 2026
AI & ML

TrueForge is TrueFoundry's open agent harness, priced against Claude

truefoundry/trueforge

An MIT-licensed TypeScript runtime for agents: model calls, MCP tools, skills, sandbox and approvals. Its cost benchmark is 14 tasks, run by the vendor.

★ 6K · TypeScript · September 22, 2026
AI & ML

FreeToken streams MoE experts to a gaming GPU on demand

FlashML-org/FreeToken

A Python and CUDA engine that keeps hot experts on the GPU, the rest in RAM, and splits misses between PCIe and the CPU. One outside test: 2.25x Ollama.

★ 13.8K · Python · September 16, 2026
AI & ML

Grok Build is SpaceXAI's coding agent, open in Rust

xai-org/grok-build

A full-screen terminal agent with headless mode and an editor protocol. The repository is a periodic sync out of a closed monorepo, not the monorepo itself.

★ 26.7K · Rust · September 12, 2026
AI & ML

Slate signs every invoice PDF and keeps its AI to drafts

slatecoil/app

Israeli invoicing that signs each document with Ed25519, gives it a public verification page, and keeps the AI to drafts a human approves.

★ 0 · September 3, 2026
AI & ML

ADHD fixes premature convergence by splitting the context

UditAkhourii/adhd

A skill that spawns parallel reasoning processes under distorted cognitive frames with no shared context, then scores, prunes traps and deepens survivors.

★ 3.6K · TypeScript · August 25, 2026
AI & ML

Colibrì runs 744B to 2.8T models off your SSD, in C

JustVugg/colibri

An engine treating VRAM, RAM and disk as one hierarchy, with a hard rule: run out of fast memory and it slows down, it never silently changes the model.

★ 24.9K · C · August 22, 2026
AI & ML

OpenScience gives a research agent 295 skills and a lab

synthetic-sciences/openscience

A browser workbench that reads the literature, writes code, runs experiments and queries UniProt, PDB, ChEMBL and thirty more databases, on your own API keys.

★ 3.2K · TypeScript · August 19, 2026
AI & ML

TurboFieldfare runs Gemma 4 26B on an 8 GB MacBook

drumih/turbo-fieldfare

A Swift and Metal runtime that keeps a 1.35 GB core resident and streams only the experts each token needs off SSD, built for Apple Silicon rather than on MLX.

★ 6K · Swift · August 18, 2026
AI & ML

A 2.78-trillion-parameter model in 8 GB of RAM, in C99

FareedKhan-dev/kimi-k3-in-c

kimi-k3-in-c streams a 1.56 TB checkpoint off disk to run Kimi K3 on an ordinary laptop CPU. No BLAS, no framework, no GPU, 176 KB of engine.

★ 5.7K · C · August 17, 2026
AI & ML

QM is an agent with a per-employee sandbox, in Slack

yc-software/qm

A multiplayer agent harness where every person and every room gets its own memory, files, keychain, crons and durable sandbox, on a harness you choose.

★ 13.6K · TypeScript · August 16, 2026
AI & ML

DeepSeek Harness: an agent runner where everything is a plugin

deepseek-ai/deepseek-harness

DeepSeek published its own agent harness, dsh, and it collected six figures of stars in two days. It is also a developer preview that promises to break.

★ 111.9K · TypeScript · August 3, 2026