Discover products

Zenith is our long-running agent harness. On Frontier SWE — seventeen of the hardest public long-horizon.

Fixture builds focused, local-first developer tools that keep agent-driven projects well tested and well organized. Makers of Flawd and Lash.

A free agent skill for your AI of choice. Draws on your league draft history, your ADP and your leaguemates’.

Create AI apps with real data, built-in payments, and users from day one. Concept to revenue in minutes.

GitNexus indexes any codebase into a knowledge graph of every dependency, call chain, cluster, and execution flow, so AI agents never miss code.

Keydris lets developers and builders control what AI agents can do before they do it. You define the authority; Keydris checks it before a governed action runs.

The agent-native macOS IDE that drives your installed Claude Code — parallel agent lanes, team chat, multi-repo.

Understand how B2B buyers research, evaluate, and choose vendors across AI search engines and agents. Ansehn is Buyer Intelligence for the Agentic Web.

You hide. An AI agent hunts you through this arena over WebMCP — it can't see your screen, only what its sensors report. Your glow, your scent trail, and every noise you make betray you. Move with WASD. Survive 3 minutes.

AI Agent Guardrails — deterministic < 2ms guardrails that block destructive tool calls, enforce declarative rules.

Wolfpack is a private, self-hosted control room for persistent coding-agent sessions across your machines.

Corsair helps AI products add secure, multi-tenant integrations with OAuth, permissions, MCP, webhooks, and hosted or self-hosted execution.

A small, self-hostable server that gives an AI agent a real phone number. SimLink relays SMS through an old.

TRACE is an open specification for hardware-attested AI agent governance records. A Trust Record states what ran, where, under which policy, touching which data, calling which tools, in a form any third party can verify without trusting the operator.

MCP-first SaaS tools for AI agents. URL shortener, pastebin, and a real send/receive mailbox.

Measure ROI of every AI dollar spent across your enterprise - Software Engineering, Sales, Marketing & Finance. Track, analyze & optimize AI productivity, AI agent performance & AI workflows. Larridin measures AI-powered work.

heyclicky is an ai assistant for your mac. it's a little buddy on screen that teaches you anything, guides you when you're stuck, and runs agents while you're away.

Ship AI agents that reason, remember, and act in TypeScript. Mastra provides memory, tools, MCP, and observability to go from prototype to production.

Research and evidence behind Harden Agentic Integrity Foundation (AIF): local cybersecurity-focused LLMs that evaluate coding-agent tool calls before execution.

Give every client its own workspace on your Mac, signed in to its own Claude Code, Codex, GitHub and cloud accounts. Fails closed. 14 days of Pro free.

Transform insights into action with the ThoughtSpot Agentic Analytics Platform—AI agents, automated insights, and embedded intelligence.

Give AI agents real website references, typography, colors, and layout context before they generate your interface.

Build AI agents that survive failure and prove their integrity. Add automatic crash recovery and cryptographically verifiable execution to your existing agent frameworks — no rewrites. Runs anywhere.

DataZen is a free open-source desktop database workspace: natural-language SQL, one-click error diagnosis, EXPLAIN analysis, charts, cross-database workflows, and a built-in MCP server for AI agents. Local-first, under 15 MB.

Share your local AI agents with your team. Claude Code, Codex, Cursor, OpenCode, and Pi get persistent identities and memory — while running on your machine. Open source.

Connect agents to the files they need, run parallel agent swarms on instant branches, and track every change through one API with sub-50ms reads and writes.

A platform for multi-agent orchestration and evaluation. Build AI agents with observability and reliability. Deploy with confidence.

FlexAI runs managed inference on 20+ open models and agent workloads through one OpenAI-compatible key, from serverless to dedicated endpoints and private cloud.

Sim is the open-source AI workspace where teams build, deploy, and manage AI agents across 1,000+ integrations and every major LLM, visually or with code.

openheim is an open-source Rust LLM agent. Interactive TUI, ACP stdio agent for Zed and JetBrains, MCP server integration, and self-hosted WebSocket server. Supports OpenAI, Anthropic, Gemini, Ollama, and any OpenAI-compatible endpoint.