AI Agent Directory

Anthropic's agentic coding tool for terminal and IDE. Understands full codebases, executes commands, handles git workflows. Uses Claude Opus 4.6 for complex multi-file reasoning.

The world's most realistic AI voice platform. Eleven v3 supports emotional expression and tonal variation. Conversational AI infrastructure for phone and web agents.

Enterprise-grade LLM for RAG and business workflows. Command R+ leads RAG benchmarks. North Data Residency for EU/US compliance. 128K context.

The seminal task-driven autonomous agent. 140 lines of Python that started the agentic AI revolution. Uses GPT-4 and vector memory.

Meta's latest open-source LLM family. Maverick (400B MoE) rivals GPT-5. Scout (17B) runs on consumer hardware. Multimodal with vision. Fully open weights.

DeepSeek V3.2 — 685B MoE open-source frontier model. Matches GPT-5 and Claude 4.5 on most benchmarks at near-zero inference cost. Freely downloadable.

Alibaba's flagship open-source LLM. 235B MoE (22B active). Multilingual, strong on coding and math. Qwen3-Coder variant matches Claude Code on HumanEval.

Open-source AI pair programmer in your terminal. Edit whole codebases, auto-commit changes with git, and use any LLM including local models. 20K+ GitHub stars.

FLUX 1.1 Pro Ultra by Black Forest Labs — current state of the art in open-source image generation. Photorealistic, fast, commercially licensable. 100M+ imag...

The most widely used LLM application framework. Chain together LLMs, tools, memory, and RAG. 100K+ GitHub stars. Powers millions of production AI apps.

Google's open-weight model family for on-device and research use. 2B to 27B parameters. Runs on laptops, phones, and edge devices. Strong safety tuning.

DeepSeek's open reasoning model that rivalled o3 at <10% the cost. MIT licensed. 671B MoE. Distilled versions (7B-70B) run on consumer hardware.

The world's first emotionally intelligent AI voice. EVI 2 detects and responds to human emotional state in real time. Used in mental health, customer service...

Single API for 200+ AI models from every major provider. One key, one format, automatic routing to cheapest/fastest model. 500K+ developers.

Lowest-latency real-time voice AI. Sub-50ms response, 70+ voices, 40+ languages. Used by AI phone agents and live translation services.

The fastest LLM inference API on earth. LPU (Language Processing Unit) hardware runs Llama 4, DeepSeek R1, Gemma 3, and Mixtral at 1000+ tokens/second.

Enterprise-grade speech AI. STT with 90%+ accuracy in 30+ languages, TTS, and real-time voice agents. Powers 200K+ developers and Fortune 500 companies.

Google DeepMind's latest video generation model. Veo 3.1 creates 4K video with native audio — ambient sounds, dialogue, music — all from a single prompt.

Enterprise conversational AI platform founded by ex-Salesforce/Google execs. Powers customer-facing AI agents for Sonos, WeightWatchers, and SiriusXM.

Microsoft's enterprise-grade OpenAI API. GPT-5, o3, DALL-E 3, Whisper with enterprise SLAs, private VNETs, content filtering, and SOC2/HIPAA compliance.

Mistral's dedicated coding model. 80B parameters, trained on 80+ programming languages. Fill-in-the-middle, instruction following, and test generation. Free ...