LatentKit
One API key. Every AI provider. Routing, fallbacks, done.
What it does
LatentKit is the control layer between your app and AI providers. Hook up OpenAI, Anthropic, Gemini, DeepSeek, Mistral — then route requests however you want. Set fallbacks, control costs, manage keys, and track usage from one dashboard. BYOK or use platform-managed access. Test chat, image gen, and embeddings in the playground. One API for every provider. Swap models, change routing, kill a provider — all without touching your code or redeploying.
Does the same job
all alternatives →
- AJAgentKit – JavaScript Alternative to OpenAI Agents SDK with Native MCP2025 · github.com · ▲64
Hi HN! I’m Tony, co-founder of Inngest. I wanted to share AgentKit, our Typescript multi-agent library we’ve been cooking and testing with some early users in prod for months. Although OpenAI’s Agents SDK has been launched since, we think an Agent framework should offer more deterministic and flexible routing, work with multiple model providers, embrace MCP (for rich tooling), and support the unstoppable and growing community of TypeScript AI developers by enabling a smooth transition to production use cases. This is why we are building AgentKit, and we’re really excited about it for a few…
- SAStartkit.ai – Boilerplate for building products with AI2024 · startkit.ai · ▲25
Hey HN! I've been serially building AI projects for over a year, and building node + js SaaS products for over 10 years with my partner. We decided to combine everything we know about AI with our node best-practices into a code boilerplate and see if it can help anyone else! We've had a bunch of positive feedback already from early-users, and at least two SaaS products being developed right now with StartKit.AI as their base. Here's what you get! → Pre-built modules for all common AI tasks: - Chat! Everything to build a ChatGPT clone or your own chatbot. With best-practice implementations of…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, May 2026
the whole month →
Parallel agents, diff reviewer, and multi-model comparisons
Dev tools · May 2026 · kilo.ai
- NW
Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…
Life & fun · May 2026 · github.com
- FM
Dev tools · May 2026 · github.com