YC (S26) | Open Computer History | Record your screen continuously locally and provide context to your agents (Claude, Codex, Openclaw, Hermes, Runner...)

Causal memory layer for AI agents — MCP server that records decision→outcome relationships. Survives compaction.

Create polished product demo videos with AI coding agents and Remotion. The UI is code, not a screen recording.

TypeScript multi-agent framework that runs in your own environment: consequential actions wait for approval and every run leaves a verifiable record. Describe the goal, not the graph. 13 built-in providers (Claude, OpenAI, Gemini, DeepSeek and more) plus any OpenAI-compatible endpoint, local models included.

Persistent, local memory for developers and their coding agents. Records commands, output, errors, and the fixes that worked into SQLite and serves them over MCP.

An open-source code repository and version control system for people and AI agents. Functions, types, recorded relationships and change history are repository data you commit, branch and merge. Look up what a change might affect before you make it. Public alpha.

Cofounder is a project harness that turns your AI coding agent into a technical cofounder.

Your coding agent starts every session blank. Rekal is the memory your team is missing

Project memory for coding agents and humans: the reasoning behind a codebase as Markdown in the repo, versioned by Git, so nothing rejected is proposed twice. No database, no daemon, no account.

Agent Beacon is the world's first open-source telemetry layer for AI agents wherever they run: locally, in CI, in the browser, or in the cloud.