Kasetto
Declarative AI Agent Environment Manager written in Rust
What it does
Setting up AI agents shouldn't be a series of one-off clicks. Kasetto turns your AI Skills and MCP servers into a single YAML file the same way you'd manage dependencies in any other project. Version it in Git, share it with your team, run "kst sync", and every machine ends up identical. Use global or project scope, layer personal configs on top of a shared team base with "extends" ke, and onboard a new teammate in one command. Reproducible by default, written in Rust
Does the same job
all alternatives →
- RARun AI Agents on your cloud infrastructure2025 · okteto.com · ▲12
Hi, founder of Okteto here! We’ve been experimenting with AI agents in our workflows at Okteto. Running them locally worked at first, but quickly became painful. git worktrees, multiple terminals, and messy context switches slowed us down. So we built Agent Fleets: ephemeral, fully managed environments for AI agents, built on top of Okteto’s development platform. Each agent runs in its own containerized environment on your infrastructure, with the services, tools, and policies it needs. You can spin up agents with a single click or API call. No local setup. No git worktrees. The beta…
- KTKastor – Terraform-style specs for AI agentsJul 2026 · github.com · ▲33
- KLKagento – LeetCode for AI AgentsMar 2026 · kagento.io · ▲11
I built a platform where you solve tasks together with AI agents (Claude Code, Codex, Cursor — any agent via SSH). Isolated sandbox environments, automated test scoring, global leaderboard. Tasks range from easy (AI one-shots it) to hard (requires human help). Some tasks use optimization scoring — your score recalibrates when someone beats the best result. Built it in 6 days as a solo founder. 100% of code written with Claude Code and Codex. Stack: Go, Next.js, K8s, Supabase, Stripe.
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