Discover the Best AI Resources

OpenAgents Control (OAC)

Wraps the OpenCode CLI with a plan-first workflow: agents propose a plan you approve before any code is written, and a ContextScout step loads your repo's existing patterns so output matches house style, not generic boilerplate.

lightonai/embeddings-pre-training

A large multi-config collection of query–document pairs assembled to reproduce and extend the mGTE/LateOn data recipe for pre-training text embedding models. Data come in source-specific configs and include per-row drop/duplicate flags and guidance for using cleaned subsets for training.

Defines a predictable repository-level instruction file for coding agents, giving teams one place to document workflow rules instead of each tool inventing its own context format.

Jarvis

Private, local-first desktop assistant for voice and text conversations that runs models on your hardware. Uses local model servers (Ollama or OpenAI-compatible endpoints), offers personal memory, dictation, TTS/STT, MCP integrations and automatic redaction; free for personal use.

Makes the spec an executable artifact: you write intent in structured markdown and AI agents generate the plan, task breakdown, and code from it. A specify CLI and slash commands drive a constitution-plan-tasks-implement workflow across 30+ coding agents.

ScaleAI/SWE-bench_Pro

Benchmark dataset for evaluating agents on long-horizon software-engineering tasks (repo-level patches, test-driven fixes). Includes golden patches, related tests, and problem statements in parquet format; aimed at agent debugging and code-modification evaluation but requires full test environments.

VibeVoice

Synthesizes up to 90 minutes of multi-speaker speech in one pass, with as many as four voices in a single conversation. Pairs continuous acoustic and semantic tokenizers at a 7.5 Hz frame rate with a next-token diffusion head on an LLM backbone.

minhxthanh/Vietnam-History-1M-Vi

A 1,000,000-sample Vietnamese historical conversation dataset in ShareGPT/ChatML format for question-answering and text-generation. Approximately 78% of samples include step-by-step reasoning chains; remaining samples are final-only. Useful for training or evaluating Vietnamese LLMs and chat agents.

Wraps Claude Code in a loop that re-runs it until a task is done, gating every exit behind two conditions — semantic completion plus an explicit EXIT_SIGNAL — so it never stops early. Adds rate limiting and a circuit breaker for unattended, headless runs.

CADAM

Generate parametric 3D CAD models from natural language and images in the browser, with real-time preview and exports to STL/SCAD. Runs client-side via OpenSCAD WebAssembly, extracts adjustable parameters, and integrates Anthropic for shape generation—suited for rapid prototyping and 3D-printing workflows.

Mini-SGLang

A ~5,000-line Python LLM inference engine that re-implements SGLang's serving optimizations — radix KV-cache reuse, chunked prefill, overlap scheduling, tensor parallelism — as a fully type-annotated reference instead of a black box.

SAM-Audio

Isolates any single sound from a complex audio mixture using a text description, a visual cue from a video frame, or a time span, returning both the isolated target and the residual. Released in small, base, and large sizes plus visual-prompt variants.