Open source · 55 reviewed
Source-available AI infrastructure a team can read, patch and run on its own hardware. Every entry records the exact licence, because the difference between Apache 2.0 and AGPL-3.0 decides whether legal signs off, and that conversation is much cheaper before the pipeline is built than after.
Open-source inference server for self-hosted LLMs. PagedAttention and continuous batching for high-concurrency serving across Nvidia, AMD, Intel and CPU backends.
Static analysis and AppSec platform where rules are readable code patterns, plus a plugin that scans every file an AI coding agent writes.
Current YOLO model family from Ultralytics: five sizes, NMS-free end-to-end detection plus segmentation, pose and oriented boxes, exportable to TensorRT, ONNX, OpenVINO and TFLite.
Postgres extension that adds vector types and approximate nearest neighbour indexes, so embeddings live in the same database as the rest of your data.
Rust vector search engine with native hybrid dense and sparse retrieval, self-hostable under Apache 2.0 or run as a managed cloud cluster.
Unitree's open robot learning stack: world models, a vision-language-action policy, Isaac and MuJoCo training environments and the SDK that drives Go2, G1 and R1 hardware.
Open-source LLM app platform from LangGenius for agentic workflows and RAG pipelines. Modified Apache 2.0: self-host freely, multi-tenant SaaS needs a commercial licence.
InfiniFlow's Apache 2.0 RAG engine built on deep document parsing. DeepDoc handles layout, tables and OCR before chunking, and every citation points back to a highlighted region in the source PDF.
Apache 2.0 vector database from Zilliz, self-hostable from a pip install up to a billion-vector cluster. The open engine under Zilliz Cloud, minus the proprietary Cardinal search core.
MPP analytics database that began as Baidu's Palo. Version 4.0 put HNSW vector indexes, BM25 full-text search and SQL-callable LLM functions into the same engine that runs the OLAP queries.
Baidu's Apache 2.0 autonomous driving platform (阿波罗). Version 11.0, January 2026, aims squarely at sweepers, delivery pods, patrol vehicles and campus shuttles rather than robotaxis.
MIT-licensed official CLI for Lark and Feishu (飞书), from ByteDance. 200+ commands and 24 agent skills over Docs, Base, Sheets, Calendar and approvals, built for AI agents.
MIT-licensed open agent framework from the MetaGPT team, prototyped in three hours as the open answer to Manus. 58,100 stars and still pushing commits in August 2026.
MIT-licensed annotation tool for images, video and 3D point clouds. Self-host via Docker, plug SAM or YOLO into Nuclio for pre-labelling, export to COCO, YOLO, KITTI and 20 other formats.
Apache 2.0 Python library and app for curating vision datasets. Query and slice samples, explore embeddings, find label mistakes and push fixes back to CVAT or Label Studio.
GPL-3.0 Blender pipeline from DLR that renders photorealistic synthetic training images with RGB, depth, normals, segmentation and exact 6D pose, exporting to BOP and COCO.
Microsoft's cross-platform inference engine for ONNX models, with execution providers for CUDA, TensorRT, OpenVINO, CoreML, NNAPI, QNN, DirectML and XNNPACK.
C/C++ LLM inference engine behind the GGUF format, running quantised models on CPU, CUDA, Metal, Vulkan, ROCm and Hexagon NPUs with no Python at runtime.
MIT-licensed co-folding models for structure and binding affinity prediction, plus BoltzGen for de novo binder design. Runs on a single GPU in roughly 20 seconds per prediction.
Firecracker microVM sandboxes for running AI-generated code. Python and JS SDKs, 24-hour sessions, pause and resume with full memory state, Apache 2.0 core you can self-host.
Serverless Postgres with copy-on-write branching and 350ms cold starts, now Databricks-owned. Its Agent Plan exists because most new databases on it are created by agents.
Google DeepMind's rigid-body physics engine for robotics. Contact-rich dynamics, MJCF models, plus MJX and MuJoCo Warp for batched GPU rollouts during policy training.
Open-source Python and TypeScript framework for RAG and agentic workflows, paired with LlamaCloud for document parsing, extraction and managed indexes.
Durable execution platform that keeps long-running agent and backend workflows alive across crashes, restarts and outages, with SDKs in Python, Go, Java, TypeScript and .NET.
Minimal open-source Python and TypeScript framework for building agents with handoffs, guardrails, sessions and sandboxed code execution, usable with non-OpenAI models.
Apache 2.0 LLM serving and quantization toolkit from Shanghai AI Laboratory's InternLM group. Builds for NVIDIA, Huawei Ascend, Cambricon and AMD ROCm from a single codebase.
Apache 2.0 agent framework from Alibaba Tongyi Lab's SysML team. Version 2.0 folded the separate Runtime project into the core, so sandboxing, agent serving and observability now ship as one...
Baidu's Apache 2.0 OCR toolkit (飞桨 PaddleOCR). PP-OCRv6 ships at 1.5M, 7.7M and 34.5M parameters, and PaddleOCR-VL-1.6 is a 0.9B document parser covering 109 languages.
Ant Group's OceanBase team open-sourced this AI-native search database under Apache 2.0 (seekdb, from the OceanBase 蚂蚁 stack). Vector, full-text and scalar filters in one SQL query, embeddable in...
PingCAP's MySQL-compatible distributed SQL database, Apache 2.0 across TiDB, TiKV and TiFlash. Vector columns and HNSW indexes ride on the TiFlash columnar replica, next to transactional rows.
Ant Group's open-source code intelligence stack (蚂蚁 CodeFuse): an Apache 2.0 GödelScript static analysis engine, MIT-licensed Ling-Coder-Lite weights and an OpenSumi-based AI IDE.
The open repos behind Unitree's robots (宇树科技): BSD-3 C++ and Python SDKs, MuJoCo and IsaacLab RL training, ROS 2 packages and XR teleoperation for data capture.
Alibaba's open model hub (魔搭社区). Apache 2.0 client library, 170,000+ open-weight models and 2,000 free API calls a day. Where most Chinese labs publish first.
Tencent's zero-dependency C++ inference library (腾讯 ncnn), BSD 3-Clause. Runs inside WeChat and QQ, with prebuilt libraries for HarmonyOS, WebAssembly, RISC-V and LoongArch.
Baidu's training and inference framework (飞桨), Apache 2.0, with kernels for Kunlunxin XPU, Ascend NPU, Hygon DCU and Cambricon MLU alongside CUDA. PaddleOCR is why most teams arrive.
Huawei's Apache 2.0 framework (昇思) built around Ascend NPUs. Development is on Gitee, the GitHub mirror is stuck on 2024 and MindSpore Lite is the built-in AI engine in HarmonyOS.
Command line vulnerability scanner for LLMs, maintained by NVIDIA. Fires adversarial probe suites at a model endpoint, scores replies with detectors, writes JSONL plus an HTML digest.
Open source CLI for LLM evaluation and red teaming. Generates adversarial cases against your prompt templates and agents, runs them in CI, reports vulnerabilities. MIT licensed.
Self-hosted LLM tracing and evals built on OpenTelemetry. Free and uncapped under Elastic License 2.0, source-available rather than OSI open source. Runs in a notebook or on Kubernetes.
Grammar, style and spelling checker for 30 plus languages. The LGPL Java core runs as a local HTTP server, so drafts never leave your machine. Cloud Premium adds closed ML rules.
Open-source multi-physics simulator for robot learning. Rigid, FEM, MPM, SPH and PBD solvers share one Python scene, with a photoreal renderer and heavy GPU batching.
Local LLM runtime with a one-command install and an OpenAI-compatible server on localhost. For laptop development, edge deployment and air-gapped environments.
Low-level orchestration framework for stateful, long-running LLM agents, with checkpointing, human-in-the-loop pauses and a managed deployment tier through LangSmith.
Document-to-Markdown engine from Shanghai AI Lab's OpenDataLab. Relicensed off AGPLv3 in April 2026, reported at 95.4 on OmniDocBench v1.6 and running on ten domestic AI chip families.
PaddleOCR's models converted to ONNX and shipped without the PaddlePaddle framework. Apache 2.0, a 27.3 MB wheel, PP-OCRv6 small by default and fully offline CPU deployment.
Alibaba DAMO's industrial ASR toolkit. MIT code, Apache 2.0 Fun-ASR-Nano weights, 1.80% Chinese CER, plus VAD, punctuation, diarization and an OpenAI-compatible self-hosted server.
Alibaba's on-device inference engine (阿里 MNN), Apache 2.0. Runs Qwen3, Qwen3-VL and DeepSeek distills on phones across CPU, OpenCL, Metal, Vulkan, CUDA and Qualcomm Hexagon.
Open source guardrails runtime from NVIDIA. Wraps an LLM app with input, retrieval, execution and output rails, plus Colang for multi-turn dialogue policy. Apache 2.0, version 0.24.0.
Apache 2.0 visual editor for Next.js and Tailwind repos. Maps DOM elements back to source lines, so canvas edits become real code changes instead of a fresh generation.
Apache 2.0 labelling tool covering images, audio, text, video and time series in one config-driven UI. Self-host free, or $99 a month for HumanSignal's hosted Starter tier.
Open-source LLM tracing, prompt management and evals. MIT core with no seat or usage caps when self-hosted, cloud from $29 a month. Acquired by ClickHouse in January 2026.
Local-first meeting notepad that records device audio instead of joining calls as a bot, transcribes on-device and keeps notes in a local SQLite file. MIT licensed, formerly Hyprnote.
Ai2's fully open family at 7B and 32B with Base, Instruct, Think and RL Zero variants. Weights, training data, every intermediate checkpoint, logs and code under Apache 2.0.
Reactive TypeScript backend where queries, mutations and durable workflows run inside the database. Agent and Workflow components handle long-running tool loops.
Open-source AI agent framework for building autonomous AI systems that can interact with tools, APIs, and environments.
Open source here means source code under an OSI or near-OSI licence. Models whose weights are downloadable but whose code or licence is more restricted are listed under open weights instead.