Vicuna
A LLaMA-based research chatbot trained on user-shared conversations to handle multi-turn dialogue.
Tools for serving, routing, evaluating and monitoring large language models
206tools listed
Pricing mix
A LLaMA-based research chatbot trained on user-shared conversations to handle multi-turn dialogue.
Manage and verify AI models, run them offline on a CPU, and serve responses locally.
A cross-platform tensor library for running large machine learning models on commodity hardware.
Create retrieval plugins that let ChatGPT search and use your own text data.
Open-source LLM customization with LoRA fine-tuning and perplexity evaluation examples.
Pre-trained English embeddings and text classifiers for Node.js, with a focus on serverless cold-start performance.
An open-source TypeScript toolkit for building AI applications and agents with streaming and multi-provider support.
A local gateway for choosing models, sharing subscriptions and masking secrets across coding agents.
An open-source programming language for AI agents with typed outputs, concurrency and built-in observability.
Open-source LLM inference and local serving for Apple silicon Macs using Metal megakernels and DSpark decoding.
Open-source AI accelerator with hardware design, a compiler, a simulator and profiling tools in one repository.
Open-source agentic reinforcement learning post-training with SGLang rollout and Megatron training.
Build Neo4j knowledge graphs from documents, videos and web pages, then query the data through chat.
Compile notes, documents, and transcripts into a self-hosted Markdown wiki with cited answers and MCP access.
Open-source tokenization library for encoding and decoding text in research and production.
Open-source LLM inference with multimodal models, local coding agents, compatible APIs, and Python and Rust SDKs.
Open-source AI gateway for model routing, SDK compatibility, request tracing and cost control.
Audit Claude Code token usage, diagnose limits, and trace context overhead from local session logs.
Open-source Kubernetes orchestration for stateful sandboxes, AI agent runtimes, and reinforcement learning workloads.
Open-source optimization of prompts, code, agent architectures, and configurations using LLM reflection.
Run Qwen Mixture-of-Experts models locally on Macs and iPhones by streaming expert weights from storage.
Open-source AI red teaming with agent, skill, MCP, infrastructure and LLM security scanners.
Desktop account management, API protocol conversion, and request routing for AI services.
Open-source PyTorch distributed training and fine-tuning for language and vision-language models
Open-source AI gateway for enterprise model routing, access control, usage attribution, and cost governance.
Pack repositories into AI-friendly files with token counts, configurable exclusions, and optional code compression.
Open-source context graphs, knowledge graphs, deterministic reasoning, and decision provenance for AI systems.
Open-source orchestration for durable AI agents, stateful applications, and replayable workflows.
Open-source local LLM inference for Metal, CUDA and ROCm, with a coding agent and HTTP server.
Persistent memory for AI agents using a Python script, an append-only log and searchable summaries.
Official Python library for the OpenAI API with synchronous, asynchronous, streaming, and Realtime support.
Open-source control plane for building, running, and scaling AI agents as REST APIs.
SkillOpt trains reusable natural-language skills for frozen LLM agents without changing model weights.
Local-first clinical entity extraction and PII de-identification across Python, Apple, Android and browser runtimes.
An open-source Python framework for building language model systems and optimizing their prompts and weights.
A shared memory hub for AI agents that turns conversations, documents, and code into reusable team assets.