Browse AI Tools

Seesa is on-premise company AI from UK maker Pentatonic: Qwen-family models, a company memory over email and documents, and approval-gated agent work installed in your building and managed for you, with SOC 2 Type II coverage.

Microsoft's open-source framework for defining MCP tool environments, running LLM agents with simulated users, and evaluating final backend state, side effects, and response requirements for reliable agent workflows.

Vicuna-13B is an open-source conversational language model from LMSYS, fine-tuned from LLaMA on user-shared conversations and released with training code, model weights, and a research demo for non-commercial use.

Agent Skills is an MIT-licensed collection of production-grade workflows for AI coding agents, with lifecycle commands and reusable skills covering specification, planning, implementation, testing, review, and shipping.

Kolibri is Aleph Alpha's Apache-2.0 open-weight German-English mixture-of-experts reasoning model with 78B total and 3.46B active parameters, up to 1M-token context, tool calling, and self-hosted vLLM deployment.

Spark-X2.5 is an Apache-2.0 open model series with compact 4B and 1.7B variants, native 1M-token context, coding and agent capabilities, and local deployment across Ollama, LM Studio, vLLM, SGLang, llama.cpp, and MLX.

Production inference platform from Prime Intellect offering OpenAI-compatible access to hosted and gateway models, with serverless endpoints, reserved capacity, multi-datacenter failover, and infrastructure for long-running agent workloads.

Pricing engine and directory that compares 366 cloud sandbox, VM, and agent-runtime providers for a given AI-agent workload, computing monthly cost from each provider's public pricing pages with a quoted source behind every answer.

AI-generated online encyclopedia from xAI that creates and continuously updates readable knowledge articles, checks proposed edits against sources, and lets readers suggest topics and corrections.

Open-source local AI agent inference benchmark from Artificial Analysis. It replays recorded agent trajectories against OpenAI-compatible model servers to measure throughput and latency on laptops and workstations.

Create and edit images with Nano Banana AI using simple text prompts.

Open-source runtime for running autonomous AI agents in policy-controlled sandboxes. OpenShell enforces filesystem, process, network, and credential boundaries outside the agent process, with auditable controls and formally checked policy changes.

Open-source, local-first document parsing library and CLI that extracts PDFs, Office files, and images into spatially grounded text and Markdown, with OCR, bounding boxes, document-complexity detection, and Node.js, Python, Rust, and WASM support.

TypeSafe AI’s System One model API for fast, typed, probability-calibrated decisions in software. Jev evaluates structured state with Choice, Score, and yes/no questions so developers can classify, route, rank, and automate workflows without parsing generated text.

Meta personal AI agent that takes action under user direction, using a persistent secure virtual machine and browser to handle web tasks, connected apps, files, and approved consequential actions.

Free, open-source desktop app for running and training AI models on local hardware, with local LLM, diffusion image/video, MLX, GGUF, audio, agent-tool, and model-serving workflows across macOS, Windows, and Linux.

Open-source continuous-improvement service for AI coding agents that captures Codex and Claude Code sessions, identifies recurring workflow patterns, and turns them into reusable skills, checks, prompts, and recommendations.

Open-source, local-first memory layer for AI coding agents that indexes Claude Code, Codex, pi, and Hermes session traces into a searchable Lance dataset, giving agents provenance-linked recall across sessions and machines.

Google Workspace AI image generation and precision editing app that creates visuals from prompts, edits individual objects and in-image text, and works directly in Google Docs, Slides, and Drive.

Open-source, local-first desktop voice AI studio for voice cloning, voice design, video dubbing, transcription, dictation, and audiobook creation, with a 646-language catalog and downloadable builds for macOS, Windows, and Linux.

Open-source agent-tool registry that gives coding agents one credential to discover and call a catalog of SEO, research, social, enrichment, advertising, and scraping endpoints, with provider rates shown and catalog usage billed from a prepaid balance.

On-demand API and tool registry for AI agents that lets them discover, inspect, and run 1,800+ tools across 59+ providers through a shared balance, with pay-per-call billing and Skill, MCP, CLI, and HTTP API integrations.

Open-source, read-only PostgreSQL observability CLI for developers and AI agents. It analyzes native database statistics, reports health and query findings, and exposes deterministic diagnostics through MCP for agent workflows.

Open-source AI video editor for people and coding agents, combining an infinite canvas, editable timeline, code-backed SolidJS compositions, a desktop dapi CLI, media understanding, generative assets, and 4K exports.