branch

@rileycx @keryilmaz @Tocelot @speedrun can you slide into our DMs 🙏🏻

@keryilmaz @Tocelot @speedrun @branchcomputer very interested in this

a16z @speedrun request for startups: GUIs for Agents we’re still in the MS-DOS era of agents today - CLI, terminal sessions, file directories deleted by openclaw etc. while a small slice of silicon valley are power users, we're SO early for the rest of the world at Speedrun, we’re looking for bold founders excited to bring the power of agents to normies everywhere. there's a whole slew of products to be built here - from agent builders to marketplaces to managed infrastructure one broad idea we’re excited about are visual abstraction layers for agents. if you don't know exactly what you want, a command line / chat interface is paralyzing - you need to see options 1 example - think of a GUI or visual command center inspired by strategy games (ex. Factorio) where agents and workflows are represented graphically. skills, tools, MCP connections, background processes, etc could all be configured and shown visually in a workspace on UX, strategy games have long perfected agent management. zoom to get a birds-eye view of your agents, batch and queue orders via shortcuts, assign agents in multiplayer etc. a well-designed agent command center would make multi-agent orchestration for normies feel easy & intuitive most folks today still haven't moved beyond ChatGPT. the potential is enormous - just as Windows unlocked mass-market use of personal computers, the right visual abstraction layer could unlock agentic work for everyone - from individuals to enterprise teams if you share our vision, we'd love to chat!

Spent today on the onboarding flow. Designs almost there, code in motion. Building this one in the open, sharing the journey as it happens.

@kloss_xyz Branch can handle this, even in very complex codebases. Coming soon.

your markdown files aren't the problem your agents are failing because... your repo has no structure if your files aren't organized like this they won't learn across repos /audits → proof (verify) /docs → description (describe) /plans → intent (plan) /specs → law (enforce) 4 folders for zero ambiguity separate your intent from proof from law from descriptions and your agents will thank you and they’ll stop guessing what files mean most people dump their .md files into /docs or their repo root and wonder why Claude Code, Codex, or Cursor agents hallucinate context don't be most people remember this and use it

Last week was brand and identity. This week is product design and code. We’re taking the time to build this right, with care, taste, and conviction. We’re builders. We’re all in on Branch now. More soon.

Branch gives teams and AI agents shared context across repositories, dependencies, interfaces, and deploy order. It’s a CLI today because that was the fastest way to make it useful. Now we’re building the full app.

A few weeks ago, Branch was just an idea between colleagues. Today it’s a CLI we use every day, and clients have already started using it too. That kind of pull is hard to ignore.

We see what's missing. That's exactly why we're here.