AI legal research agent

RAGFlow

RAG · Multi-model

8.1

Open-source RAG engine with deep document parsing, hybrid search, and visual agent orchestration.

CAI

Agents · Multi-model (incl. alias1, GPT, Claude, DeepSeek)

7.3

Open-source agent framework for offensive security, bug bounty automation, and AI-driven penetration testing.

Epsilla

RAG · Multi-model

7.3

Agent-as-a-Service platform with managed RAG and a no-code builder for vertical enterprise AI.

PageIndex

RAG

7.0

Vectorless reasoning-based retrieval for long documents, with traceable, auditable answers.

Octomind

Agents · Multi-provider: OpenAI, Anthropic (Claude), DeepSeek, Ollama, and 20+ others; benchmarks cite GLM-5.2 and Claude Opus

Homebrew for AI agents: install specialized, budget-capped AI specialists with one command.

TokenPath

RAG · model-agnostic (works with any LLM output; uses in-house attribution model)

Token-level citation and attribution API for AI-generated answers

Claude

Featured

Writing · Claude Opus / Sonnet

9.6

Anthropic's flagship assistant for long-form writing, analysis, and coding.

LlamaIndex

Featured

RAG · BYO (Claude / GPT / open)

8.7

Data framework for connecting LLMs to your data.

Udio

Audio · Udio (proprietary)

8.8

Suno's main rival for AI-generated full songs.

Ernie Bot

Agents · Baidu ERNIE 4.0 / ERNIE X1 / ERNIE Turbo (in-house)

8.7

Baidu's Mandarin-first ChatGPT rival, powered by the ERNIE model family

Google Vertex AI

Agents · Gemini 2.5 (Pro/Flash/Nano), Imagen, Veo, Chirp, plus Model Garden (Llama, Mistral, Claude via partner)

8.6

Google Cloud's unified platform for building, deploying, and scaling enterprise AI agents and models.

Glean

Agents · Model-agnostic: routes across 35+ LLMs including GPT-4o, Claude 3.5/4 Sonnet, Gemini 1.5/2, Llama 3, Mistral, plus Glean in-house models

8.5

Work AI platform that unifies enterprise knowledge, search, and agents

Semantic Kernel

Agents · Multi-model

8.4

Microsoft's open-source SDK for wiring LLMs, plugins, and agents into enterprise .NET, Python, and Java apps.

Yi (01.AI)

Agents · Yi-Lightning (MoE), Yi-Large, Yi-1.5 (6B/9B/34B), Yi-VL, Yi-Coder — in-house 01.AI foundation models

8.4

Foundation models from 01.AI — open-weight Yi family plus frontier Yi-Lightning and Yi-Large

ClearML

Agents · Model-agnostic

8.3

End-to-end MLOps and GenAI platform with open-source experiment tracking and enterprise GPU orchestration.

Grain

Audio · Claude, ChatGPT

8.3

AI meeting notes, coaching, and an MCP feed for your agents

H2O.ai

Agents · Multi-model

8.3

Enterprise AI platform combining AutoML, generative AI, and vertical agents for regulated industries.

Qwen

Writing · Qwen3 / Qwen-Image / Qwen-MT / Qwen3Guard

8.3

Alibaba's open-weight foundation model family covering chat, vision, image generation, translation, and safety classification.

Giskard

Evaluation · Multi-model

8.2

Continuous AI red teaming platform that stress-tests LLM agents for vulnerabilities before they hit production.

Hermes Agent

Agents · Multi-model (300+ via Nous Portal)

8.2

Open-source multi-channel AI agent with persistent memory, scheduling, and subagent delegation from Nous Research.

Msty

Writing · Multi-model (Ollama, Claude, GPT, Gemini, others)

8.2

Privacy-first desktop AI workspace that runs local and cloud models side by side.

Writer

Writing · Palmyra (in-house)

8.2

Enterprise generative AI platform built around in-house Palmyra LLMs for regulated, brand-consistent content.

Berkeley Function-Calling Leaderboard

Evaluation · Multi-model

8.1

Open benchmark from UC Berkeley that ranks LLMs on real-world tool-use and function-calling accuracy.

Kimi

Writing · Kimi K2 (K2.5 / K2.6 / K2.7 Code)

8.1

Moonshot AI's chat assistant with long-context document analysis, coding agents, and deep research built in.

Le Chat

Writing · Mistral Medium 3.5 / Small 4 / Voxtral

8.1

Mistral's ChatGPT-style assistant, now an agent that browses, codes, and plugs into your work tools.

CAMEL-AI

Agents · Multi-model

8.0

Open-source Python framework for building multi-agent systems and synthetic data pipelines.

ChatGPT

Writing · GPT-4o, GPT-4.1, o-series reasoning models

8.0

OpenAI's flagship conversational assistant, and the default benchmark every other chatbot is measured against.

Exa

RAG · Proprietary neural + keyword search

8.0

Web search API built for AI agents, with structured outputs and token-efficient highlights.

Hume AI

Audio · Octave, EVI, TADA

8.0

Emotionally intelligent voice AI with expressive TTS, speech-to-speech, and human-feedback evaluation APIs.

Sesame

Audio · Sesame CSM (1B / 3B / 8B)

8.0

Conversational voice AI aiming to cross the uncanny valley with context-aware, emotionally aware speech.

Khoj

Agents · Multi-model

7.9

Open-source personal AI that builds agents, searches your documents, and automates research across local files and the web.

Manus

Agents · Multi-model

7.9

Generalist agent for research, code, and web tasks.

Humata.ai

RAG · Multi-model

7.8

Chat-with-your-documents RAG tool with citation-backed answers across uploaded PDFs and files.

Patronus

Evaluation · Platform (any LLM)

7.8

Automated LLM evaluation for hallucinations, safety, and quality.

STORM

Writing · Multi-model (via LiteLLM)

7.5

Stanford's open-source research agent that turns a topic into a Wikipedia-style article with citations.

Agent Lightning

Agents · Multi-model

7.3

Microsoft's open-source trainer that fine-tunes AI agents with RL and prompt optimization, framework-agnostic.

DeepSeek

Coding · DeepSeek R1, V3, V2, Coder V2, VL

7.3

Chinese AI lab shipping open-weight reasoning models that punch well above their API price.

FedML

Fine-tuning · Bring-your-own (PyTorch, Hugging Face)

7.3

Distributed training, fine-tuning, and serving platform with federated learning roots.

Gemini

Writing · Gemini 2.x (Flash / Pro / Ultra)

7.3

Google's flagship multimodal AI assistant with deep integration into Workspace and Android.

Gorilla

Agents · gorilla-openfunctions-v2 (6.91B)

7.3

Open-source LLM purpose-built for function calling and API invocation across thousands of tools.

OpenBB

Agents · Multi-model (Agent Rita is model-agnostic)

7.3

Open-source financial workspace where analysts and AI agents share the same governed data.

Cognee

RAG · Multi-model (Claude, OpenAI, others)

7.2

Open-source graph-memory layer that gives AI agents persistent, queryable context across sessions.

DeerFlow

Agents · Multi-model (Doubao, DeepSeek, OpenAI, Gemini)

7.2

Open-source multi-agent framework from ByteDance for long-running research, coding, and content tasks.

Domino Data Lab

Agents · Multi-model

7.2

Enterprise AI platform for building, deploying, and governing models and agents at scale.

Graphiti

RAG · Multi-model

7.2

Open-source temporal knowledge graph framework for building agent memory that updates in real time.

Hermes One

Agents · Multi-model (BYO via OpenRouter/OpenAI/Anthropic/Gemini/xAI/Ollama)

7.2

Open-source desktop AI agent with a self-improving learning loop and multi-platform messaging connectors.

Inspect AI

Evaluation · Multi-model

7.2

Open-source LLM evaluation framework from the UK AI Security Institute with 200+ built-in benchmarks.

mini-SWE-agent

Agents · Multi-model (via litellm, OpenRouter, Portkey)

7.2

A 100-line open-source coding agent that scores 74%+ on SWE-bench Verified.