key-carousel - Key rotation for LLM agents
I think in-process key management is the right abstraction for multi-key LLM setups. Not LiteLLM, not a Redis queue, not a custom load balancer. The failure modes are well-understood: a key gets rate-limited, you wait, you try the next one. Billing errors need a longer cooldown than rate limits. This is not a distributed systems problem — it's a state machine that fits in a library. The problem is everyone keeps solving it with infrastructure instead. Spin up LiteLLM, now you have a Python service to maintain. Reach for Redis, now you have a database for a problem that doesn't need one.…
What it does
In the maker’s words, at launch
I think in-process key management is the right abstraction for multi-key LLM setups. Not LiteLLM, not a Redis queue, not a custom load balancer. The failure modes are well-understood: a key gets rate-limited, you wait, you try the next one. Billing errors need a longer cooldown than rate limits. This is not a distributed systems problem — it's a state machine that fits in a library. The problem is everyone keeps solving it with infrastructure instead. Spin up LiteLLM, now you have a Python service to maintain. Reach for Redis, now you have a database for a problem that doesn't need one. key-carousel manages a pool of API key profiles with exponential-backoff cooldowns: 1min → 5min → 25min → 1hr for rate limits, 5hr → 24hr for billing. Falls back to OpenAI or Gemini when Anthropic keys are exhausted. Optional file persistence. Zero dependencies.
Does the same job
all alternatives →
- ECErgonomically call LLM in bulk from CLI2025 · github.com · ▲7
Hi! I've found myself repeatedly writing little scripts to do bulk calls to LLMs for various tasks. For example, run some analysis on a large list of records. There are a few "gotchas" to doing this. For example, some service providers have rate limits, and some models will not reliably return JSON (if you're asking for it). So, I've written a command for this. What I've tried to do here is let the user break up prompts and configuration as they see fit. For example, you can have a prompt file which includes the API key, rate limit, settings, etc. all together, or break these up into…
- IBI built a firewall for agents because prompt engineering isn't securityJan 2026 · github.com · ▲7
Hi HN, I’m the creator of Cordum. I’ve been working in DevOps and infrastructure for years (currently in the fintech/security space), and as I started playing with AI agents, I noticed a scary pattern. Most "safety" mechanisms rely on system prompts ("Please don't do X") or flimsy Python logic inside the agent itself. If we treat agents as autonomous employees, giving them root access and hoping they listen to instructions felt insane to me. I wanted a way to enforce hard constraints that the LLM cannot override, no matter how "jailbroken" it gets. So I built Cordum. It’s an open-source…
- LOLlaMaKey – One master key for all cloud LLM/GenAI APIs2024 · github.com · ▲6
Key management for multiple users and multiple cloud LLM/GenAI APIs is difficult to be both safe and convenient. Sharing keys among users risks leaking the key and makes it difficult to curb the leakage without interruptions. But assigning one key per user per cloud API results in too many keys to keep track of. Meet LlaMa(ster)Key, the secure and easy solution for API key management: * For each user, one master key for multiple APIs. * The master key is unique to each user. Granting and revoking a user's access won't impact other users. * The actual API keys to authenticate with cloud…
- MLMakes local LLMs faster and more reliable by optimizing for your deviceJun 2026 · autotunellm.com · ▲6
Time to first token is 39% faster Agent wall times decrease by 46% No swaps Tracks your resource usage in real-time and adjusts how the model runs so that it works perfectly on your device. Implements KV cache sizing, prefix caching, live RAM pressure management, context trimming, KV quantization, and more. Built a ton of features
- ISI spent 8 months trying to make LLMs Hack2025 · ▲6
Hey HN! For that last 8 months I've been trying to make agents that can hack web applications to find vulnerabilities in them - An AI Security Tester. The system has 29 agents in total, a custom LLM Orchestration framework which works on the task-subtask architecture (old-school but works amazingly for my use case, and is pretty reliable) with custom agent calling mechanism. No Auo-Gen, Langchain and Crew AI - Everything custom built for pentesting. Each test runs in an isolated Kali linux environment (on AWS Fargate), where the agents have full access to the environment to undertake any…
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 · 26d ago · cactuscompute.com
Launched alongside, March 2026
the whole month →
Switch from ChatGPT to Claude with import memory feature
AI · Mar 2026 · claude.com
