open source

Open-source text annotation for classification, NER, and seq2seq tasks.

Leading open-source image/video annotation with auto-annotation and team workflows.

Open-source, highly configurable labeling for text, images, audio, video, and chat.

Attention-free RNN-style open models with transformer-level performance and constant-memory inference.

Fully open multimodal (images/video+text) models & training stack; strong results and reproducible recipes.

Open (MIT-licensed) reasoning model with distilled 1.5B–70B local checkpoints; known for chain-of-thought quality.

Open-source deep-research agent built on LangGraph; configurable models, tools, and MCP servers.

Dev-first open-source autonomous agent framework for building and running multi-step agents.

Open-source platform for autonomous software development agents that execute multi-step work.

Open-source enterprise search & chat over docs, respecting permissions.

Open-source framework for retrieval, pipelines, and chat over files (on-prem friendly).

Open-source agent that scopes topics, investigates the web, and writes cited research reports.

Open-source framework to build doc/chat RAG pipelines and agents for production.

Self-hostable enterprise search + chat over company docs, Slack, GitHub, and more.

Code-specialized model family (0.5B–32B) with competitive generation and reasoning.