Codevisor is a native Mac and iPhone app for Claude Code, Codex, Pi, and any ACP coding agent. Run agents side by side in isolated worktrees, on every machine you own.
Product
- Founded
- 2023
- Team
- 2 people
Browser storage is unavailable. Keep this page open and export your collection before leaving.
Codevisor is a native Mac and iPhone app for Claude Code, Codex, Pi, and any ACP coding agent. Run agents side by side in isolated worktrees, on every machine you own.
Product
Butter is building bVisor, an incredibly lightweight sandbox runtime for AI agents.
Founders · Product
WOZCODE is the highest performing AI coding plugin for Claude Code. 80% on TerminalBench 2.0, 5–10× faster, 25–50% cheaper. Install in seconds — no signup required.
Founders · Product
We research the psychology of how LLMs learn, and turn it into new training techniques that train custom models and harnesses together.
Founders · Product
Compyle automates the production work behind every Phase I ESA — from data collection through draft report — so your EPs can take on more projects without taking on more hours.
Founders · Product
Inkbox gives AI agents an identity, communication channels, and their own computer.
Founders · Pricing · Product · How it works
Firebender is the most powerful coding agent for Android engineering. One-click install from the IntelliJ plugin marketplace to your IDE. It has context over your codebase and lets you use the best models for asking questions…
Founders · Product
TrainLoop makes it effortless for developers to supercharge LLM performance through reinforcement learning.
Founders
Quetzal is the first fully LLM-powered translation and internationalization suite, enabling companies to translate and internationalize their software and content instantly with minimal setup. We also handle all of your…
Pricing · Product
Turn videos into structured data with Dragoneye zero-shot vision models. No data labeling or model training.
Founders · Product · How it works
Formal verification and AI — research and engineering from Theorem.
Founders · Product
RunAnywhere makes the best open models faster and cheaper to run, for everyone. Wally serves frontier open models through one API key and one CLI, and our open-source SDKs run models on the device.
Founders · Product
Let your coding agent both write code and build infrastructure to run it
Founders · Product
Cuebench builds RL environments for scientific discovery and inference.
Create and orchestrate powerful AI coding agents. Use any model, including frontier, open-weight, and locally deployed ones.
Founders · Product
Unlimited DeepSeek V4.1 Flash and GPT-6 Luna on every plan. Every other model runs through 1 OpenAI-compatible API with failover built in.
Founders · Product
Open-source platform to trace, evaluate, and debug AI agents. Laminar surfaces agent failures, and helps you fix them.
Founders · How it works
Wafer serves open models on a stack tuned to your real traffic, layer by layer: model, decoding, engine, kernels and hardware.
Product
Managed Claude Code agents in the cloud. Define agents as config files in your repo – Ellipsis runs them to build features, fix bugs, and investigate production issues.
Founders · Pricing · Product
We're building a protocol for large language models to directly interface with image sensors.
World's fastest iOS & Android app builder. Production-ready mobile apps that deploy directly to App Store & Google Play in minutes.
Customers · Product · How it works
Use Pakistan's best AI calling platform to automate appointment booking, lead qualification, and routine customer service. 100+ realistic Urdu voices. APIs for Text to Speech (tts). Try for free.
Founders · Origins · Product · How it works
Okibi generates a CLI from your product, so agents can use it fully on their own.
Founders · Product
We handle the infra so you can focus on building agents that search, scrape, and interact with the web at scale.
Founders · Product