Open-source React components and runtimes for building AI chat. Streaming, tools, and persistence in TypeScript.
Customers · Founders · Product
- Founded
- 2024
- Team
- 3 people
Browser storage is unavailable. Keep this page open and export your collection before leaving.
Open-source React components and runtimes for building AI chat. Streaming, tools, and persistence in TypeScript.
Customers · Founders · Product
Airweave is an open-source context retrieval layer that lets AI retrieve relevant context from apps and databases by acting as a shared information retrieval layer between AI systems and data sources.
Product · How it works
BrowserOS neo, formerly BrowserClaw, is a local, open-source browser your AI agents (Claude, Cowork, Codex, Cursor) drive using your logged-in accounts. Watch every step, run agents in parallel, replay any session. Free.
Founders
Turn your ideas into products without coding, all on one platform.
Founders · Pricing · Product · How it works
145k+ GitHub stars. Shared context of codebase for agents and developers. Start free, or run it locally.
Founders · Pricing · Product
Supercharge your AI agents with data from the web and beyond. Building the library for superintelligence. 🔥
Pricing · Product
The best way to reach humans instead of spam folders. Deliver transactional and marketing emails at scale.
Founders · Pricing · Product
Lamina Labs builds the visualization layer for AI. Turn any PDF, slide deck, doc, or prompt into a narrated 1080p whiteboard explainer video in ~40 seconds with Simi — in the web app, Python & Node SDKs, or MCP server. Backed by Y…
Founders · Product
Zatanna maps human-only software workflows and exposes them as reliable APIs your AI agents and internal tools can call in production. No browser automation scripts to maintain.
Product · How it works
Luminal is an AI inference compiler that compiles and optimizes AI models for GPUs and ASICs, delivering the fastest, highest throughput inference in the world.
Founders · Product
Centauri AI builds trusted AI products for DataCube, coding-agent operations, and agent orchestration.
Founders · Product · How it works
Monte helps companies build specialized models for AI agents that continuously learn from organizational knowledge. Research-first, embedded with your team.
renderlet is a framework that makes it easy to develop interactive applications. Building applications with high-performance graphics is very hard – existing tools are cumbersome and aren’t truly platform agnostic, leading to…
Founders · Product · How it works
Speko is the OpenRouter for Voice AI, the first proxyless, zero-latency model router for voice AI. It routes STT, LLM and TTS on numbers from the independent benchmark at speko.ai/benchmarks. The benchmark covers 89 speech and language…
Founders · Product
Capy is the best AI software engineer. Delegate tasks to parallel coding agents that plan, build, and ship — from task to merged PR.
Pricing
RunRL improves LLMs and AI agents with reinforcement learning. Do you have a model that needs to get better at a certain task? Are you tired of messing around with prompts? Do you spend a lot of money on observability, and wish that all…
Product
Understand your codebase at a glance with intelligent code visualization
Product
Zep is the enterprise context layer for reliable agents, providing governed access to company knowledge and skills built from agent tasks.
Founders · Product
Modelence runs your app in production for you: managed database, auth, backups, scaling and AI-monitored infrastructure from the first deploy. Start free.
Customers · Founders · Pricing · Product
browser infrastructure for ai agents and web automations. managed auth, reusable sessions, fast spin-up, and autoscaling browsers.
Founders · Pricing · Product
Emergent builds autonomous coding agents that replace traditional software development by generating, testing, and deploying production applications directly from plain-language intent. Our systems run in production at global scale and…
Founders · Pricing · Product · How it works
Cut OpenAI, Anthropic, and Gemini API costs with accuracy held flat — or take a smaller cut and lift accuracy by several points instead. The bear-2 prompt compression API strips low-signal tokens from your inputs before they hit the…
Product
Describe what you want to build, and Bitrig turns it into real Swift code you can ship to the App Store.
Founders · Product · How it works
Automorphic has invented a way to infuse knowledge into LLMs via fine-tuning (surpassing context window limitations), enabling developers to rapidly iterate on and successively improve custom models cheaply and efficiently.
Founders · Product