AI Tools

Orchestrate multi-agent AI workflows for full-stack development

Intent-driven multi-agent orchestration framework - say what you want, an adaptive engine plans, schedules across CLIs, executes, and verifies it.

claudecodexgemini

91 11 days ago

Deploy hardened containers with declarative isolation

Security-hardened, declarative Linux container runtime for AI agents and production services - Nix-native, 12ms cold start, not a Docker replacement.

nixnixossystemd

91 11 days ago

Execute untrusted Python code in isolated Docker containers

TakoVM runs agent code in isolated Docker/gVisor sandboxes with built-in job queues, execution history, and replay.

dockerpostgrespython

Train and run byte-level transformer models on CUDA

gpt is a hackable CUDA/C transformer implementation that trains on raw bytes, with causal attention, RoPE, and AdamW.

cudaopenblasgit

91 21 days ago

Render Office documents in the browser with WebAssembly

Browser-based, read-only DOCX/XLSX/PPTX viewer with Rust/WASM parsers and Canvas 2D rendering - fast, bundle-conscious, and built entirely by AI agents.

vscodenpmwebpack

91 11 days ago

Generate hands-on technical tutorials for learning by doing

Lathe generates hands-on, multi-part technical tutorials you work through yourself in a local UI, with opt-in verification and sourced provenance.

githubclaudecursor

Build production-grade GenAI agents with type-safe Python

Typed Python AI SDK for building agents that run anywhere - web, terminal, voice, or durable background queues - with any model.

openaianthropicgemini

91 10 days ago

Benchmark LLM agents on fixing real-world CVE vulnerabilities

Benchmark for evaluating LLM agents on fixing real-world CVEs inside sandboxed Docker containers, scored against maintainer tests.

dockeropenaianthropic

91 3 months ago

Reduce AI token costs by filtering CLI output

lowfat is a lightweight CLI that filters verbose shell output and file content before it reaches an AI agent, cutting token cost.

claude claudeopencodepi

Review Code Changes with AI-Powered Line-Level Feedback

Open Code Review (ocr) is Alibaba's AI code review CLI, trading some recall for high precision at about 1/9 the tokens of a general agent.

gitgithubnpm

Accelerate LLM inference with variance-normalized KV-cache

vLLM KV-cache quantization backend that gives 3-5x more cache capacity and up to 1.3x throughput over FP16, at FP16-level accuracy.

vllmhuggingface

91 3 months ago

universal sqliteollamaopenai

Query & move data Tool

Build persistent knowledge graphs from LLM conversations

Local-first memory sidecar that builds a persistent knowledge graph from LLM conversations and injects scored context into prompts.

91 3 months ago