routstr's avatar
routstr
_@routstr.com
npub130mz...l29s
A Decentralised LLM Protocol & Routing Marketplace Check our docs: https://docs.routstr.com Try the chat app: https://chat.routstr.com Github: https://github.com/routstr
routstr's avatar
routstr 20 hours ago
Google seems to be making a comeback with their new model, Gemini 4 Neon. You can try it out via 5 Routstr nodes already without getting another subscription or having to reveal your identity. Note: All new models are by default available via Routstr nodes. image
routstr's avatar
routstr 2 days ago
Routstr Core v0.5.1 πŸš€ Postgres: a node is no longer one process deep. Run multiple workers or replicas against one database. Existing keys.db imports itself on first boot. Image generation: /v1/images/generations is live and billed per image. OpenAI, OpenRouter, Together, Venice. Stats: your node now signs a per-day, per-model report to Nostr (kind 38422). Corrections replace instead of adding, and days it couldn't collect show up as gaps instead of reading as zero. And other fixes: β€’ 402s carry real numbers now β€” required, available and shortfall msats, plus the formula that produced them β€’ OpenRouter can no longer charge above the listed price β€’ Hung-up streams, 1-hour cache writes and stopped Messages streams bill correctly image
routstr's avatar
routstr 1 week ago
routstrd v0.5: Model Paths and Open Algorithms πŸ“Š This brings us one step closer to our vision for an LLM marketplace built on Nostr. To try out our curator of model paths, update first using: `rout update` and turn on model paths: `rout models auto-model-path on` Learn more about it and join us by becoming a curator of inference providers πŸ‘‡ View article β†’
routstr's avatar
routstr 3 weeks ago
Permissionless aggregation is an interesting phenomenon. Most new models are by default available on the Routstr network because different nodes serve models from different sources. You fetch Nostr events, you pay with sats. Models become automatically available on Routstr when any of upstreams start offering them: 1. OpenRouter 2. Venice 3. PPQ 4. Tinfoil 5. Fireworks 6. Deepseek 7. OpenAI/Anthropic of course 8. And more. (We hope to see more diversity of upstream providers) Similarly, these Abliterated models are now available from various routes. Your client -> Venice Your client -> PPQ -> Venice Happy red teaming your own tools. image View quoted note β†’
routstr's avatar
routstr 3 weeks ago
Open weights just caught up with the closed frontier, for building and for defending! Kimi K3.1 Pro and Kimi K3.1 Pro Ultraspeed are both live on the Routstr network. Building: #4 in Artificial Analysis Intelligence Index. #2 in Terminal Bench 4.0, only behind Opus 5.5. Cyber Defense: #2 in AA Cyber Index, but #1 among publicly available models. And it doesn't refuse the work. Try them, model: kimi-k3.1-pro / kimi-k3.1-pro-ultraspeed Happy building and defending.
routstr's avatar
routstr 0 months ago
LiteLLM was compromised again, your Routstr node is not affected. A malicious build of litellm 1.107.0 shipped last week with a credential stealer and remote-code loader in all seven wheels. It's the second litellm hijack this year. Routstr is unaffected. We pin litellm >=1.101.2,<1.102 with an exact lockfile, so 1.107.0 can't resolve in a Routstr deployment, and we found none of the published indicators in our environments. If you are running your own venv as a developer, check "pip show litellm". If it says 1.107.0, remove cook.pth, cook.py, and sitecustomize.py from site-packages before running pip again, startup re-triggers the payload, then treat every secret on that host as compromised and rebuild. We're removing litellm. We only use it as a translation layer, and two hijacks in one year is not a good sign.
routstr's avatar
routstr 1 month ago
New Release: Routstr Core 0.5.0 A Major New Feature: Modular Model Path Control. With this new release, any client can specify the exact upstream inference provider they want to use for a particular model. Including all the inference providers on OpenRouter. Second Major Feature: Upstream Provider Test Suite You can test if everything is good with an upstream inference provider you just added. Other changes in: 1. Intelligence: β€’ /v1/systemone β€” typed AI decisions, paid per call (Jev) β€’ /v1/decisions β€” OpenAI's new Decisions API, proxied β€’ native Venice + DeepSeek 2. Money: β€’ Lightning refunds + payouts in tx history β€’ crash-safe refund claims 3. Ops: β€’ one-command private node onboarding and llms.txt for agent powered onboarding β€’ faster requests, provider cooldowns, never strand a reservation ~100 PRs. 254 files. 4 weeks. image
routstr's avatar
routstr 1 month ago
Not just a problem with secondary markets for AI inference, it solves this problem for anything that is resold online using an API key. Please help us battle test it! View quoted note β†’
routstr's avatar
routstr 1 month ago
Unreal times, an idea from a conversation here on Nostr to full implementation in 2-3 days. Juraj is a juggernaut! Open ideas, open execution. Open source will be unstoppable. Grateful for this community. ❀ View quoted note β†’
routstr's avatar
routstr 1 month ago
The upcoming Private Provider App goes head-to-head with Codex Desktop and Claude CoWork but it's built entirely on Nostr rails, so it'll be 10x better, with none of the legacy headaches like API keys, GitHub connections, Google 🀧, etc. But unlike Codex/Claude, you aren't leaking personal information because of TEEs and you only need to topup using some Bitcoin! Plus, everything is on your phone so you can build while playing with your kids and touching grass. 🧑 Super excited! View quoted note β†’
routstr's avatar
routstr 2 months ago
Jev is live on Routstr! Jev jev jev jev jev, I'm sure you've heard of this by now, it's a new model architecture that is super fast and super cheap and works as classifier for anything you need. Look here for more inspiration: You can finally jevelop (sorry πŸ˜‚) using jev using nothing but a couple of sats! Update your routstrd if you want to use it through it. Or you can use it through our sdk as well. (pnpm install @routstr/sdk) The model is "jev-latest" live on one node rn: Give this skill to your agent and start building using this, just tell it to use and query
routstr's avatar
routstr 2 months ago
We Sunset Our Official Node. Zero Downtime. All nodes are community-run now 🧑 It's been a month and a half since we sunset api.routstr.com, the last "official" Routstr node. Nobody noticed a thing. routstrd and routstr-sdk discover nodes on Nostr and pick the cheapest one for you automatically. No one can rugpull you. No one can capture you. Your client truly works for you. We're removing the team as a dependency. Point out any centralization left and we'll remove it next πŸ”¨
routstr's avatar
routstr 2 months ago
New routstrd Release: Faster than Ever Before πŸƒβ€βž‘βš‘οΈ Update using: routstrd update New Features: - Prompt Caching inside TEE models via Tinfoil (GLM 5.3 and GLM 5.3 Flash are new) - Faster Responses with Proactive TopUps - New Binary Release thanks to @hzrd149 (download binaries directly from here: https://github.com/Routstr/routstrd/releases/tag/v0.4.10) Major Bug Fixes: - Tinfoil 422 error which is due to stale Tinfoil keys - Lightning topups sometimes requiring restart is fixed - Frequent parallel requests failing due to 402 errors Please report any bugs/issues you find, we'll zap you :) image
routstr's avatar
routstr 2 months ago
Cuba Bitcoin Cashu mint is down right now. This was set as the default mint for routstrd, please switch to another mint to continue using Routstr. routstrd wallet mints set-default routstrd receive 21000 You can then continue using Routstr. We're sorry about the inconvenience. We're in search of more mints.
↑