News for hackers. Stuff that matters.

hestefisk

hestefisk on Hacker News

Show HN: Recursant, the agent-aware model router built for hybrid workloads

Posted by hestefisk on Monday October 05, 2026 @12:01AM
from the show-hn dept.

https://github.com/ajensenwaud/recursant/

Sharing Recursant, the agent-aware model router for private/public workloads. Cut your AI agent bill by 30% and seamlessly operate agents across private and public inference infrastructure. Recursant is agent-aware, routes intelligently, built to be fast (C), and intended for privacy.github.com/ajensenwaud/re…It’s still rough around the edges, but good enough to run across private/public...

( Read More... | no comments | on HN )
Re:An index site of agent harnesses on Wednesday July 08, 2026 @07:56AM (#48830770)
I have compiled a list of the most popular agent harnesses in one place. I hope you find it useful. MCP service provided.
Re:Varela: Neuromancer-inspired 3D self-mutating coding harness on Saturday July 04, 2026 @01:31AM (#48782868)
I know there is a lot of AI slop being submitted here, but I will take the chance.

I built a self-mutating multi-agent coding harness, Varela (named after Francisco Varela, the famous researcher of living systems and intelligence).

Varela has two modes - a nice TUI as well as a Neuromancer-inspired cyberpunk 3D world where you interact with the agents with visual animations of sub agents, tool calls, etc.

The latter is probably not very practical, but I see it as a nice tribute to William Gibson's Neuromancer, which I love. Feel free to submit a cyberdeck as a PR.

Comments or code welcome.

Show HN: Recursant, a mesh-based control plane for AI agents

Posted by hestefisk on Wednesday May 13, 2026 @03:46AM
from the show-hn dept.

https://github.com/ajensenwaud/recursant

I have submitted before, but it didn’t end up in the Show HN list for some reason.I have built Recursant, an AI agent governance platform that governs agents across stacks and clouds to maintain compliance. In many large enterprises this is a real compliance issue with different teams using different frameworks and runtime environments, which creates control risk.I hope to get some feedback on...

( Read More... | no comments | 2 points | on HN )

Show HN: Recursant – service mesh for governing AI agents

Posted by hestefisk on Wednesday May 06, 2026 @09:57AM
from the show-hn dept.

https://www.recursant.ai/

Hello,I have just released Recursant to the public. I have been working on it for a while. It is a control plane for governing AI agents across stacks. It provides full observability, guardrails, and control on the network level by routing all traffic through a side car.Problem statement: many large, regulated enterprises (think banks, telcos) have one engineering team on LangGraph, another on...

( Read More... | 1 comment | 2 points | on HN )
Re:ClawLock: The Control Plane for OpenClaw on Wednesday April 01, 2026 @05:52AM (#47598822)
I love OpenClaw and what it can do. I have long been wanting OpenClaw to take care of my shopping and purchases online. However, with the current threat of prompt injections, I do not trust it with my credit card details as it stands.

To reduce the chance of breaches, I built ClawLock, a supervisor (sidecar with process isolation) for OpenClaw that injects controls around tool use. The user defines a passport for what the tools can and cannot do and ClawLock governs it. For high-risk transactions like in-browser purchases or shell command, a deterministic policy engine and an LLM-as-judge are used to detect any potential threats prior to execution.

ClawLock is currently in its infancy. It is primarily tested on Linux. I would appreciate any feedback on your experience using it on MacOS and WSL.

Re:Thousands of CEOs just admitted AI had no impact on employment or p... on Wednesday February 18, 2026 @03:35AM (#47058712)
I am in strategy consulting and I can tell you the productivity gains are real in terms of research, model building, and summarising work. The result is price pressure from our clients.
Re:Clawdbot - open source personal AI assistant on Monday January 26, 2026 @06:01AM (#46764185)
This is really cool, nicely done. Q: How did you get the WhatsApp integration working? I thought that was completely closed off unless you are in Europe.
Re:Kagi releases alpha version of Orion for Linux on Saturday January 10, 2026 @06:35AM (#46564842)
Also Ladybird is quite an interesting alternative. Anyone here using it day to day?
Re:I built a tool to create AI agents that live in iMessage on Friday January 09, 2026 @04:42AM (#46551907)
I get timeouts on the app. Not impressed, sorry.
Re:Venezuela's capital hit by explosions, smoke seen on Sunday January 04, 2026 @03:44AM (#46486177)
Not respecting international law?
Re:I failed to recreate the 1996 Space Jam Website with Claude on Sunday December 07, 2025 @02:31PM (#46184340)
Would be interesting to see whether Gemini could crack this problem.
Re:Slack's 57MB 404 page on Friday July 11, 2025 @05:14AM (#44529989)
No. Everyone is on Teams.
Re:David Lynch has died on Thursday January 16, 2025 @02:17PM (#42729621)
https://www.theguardian.com/film/2025/jan/16/david-lynch-twi...
Re:Stonebraker Seeks to Invert the Computing Paradigm with DBOS on Saturday August 31, 2024 @05:35AM (#41407602)
And the network is the computer :)
Re:Richard Stallman, su, and the 'wheel' group (2004) on Sunday June 23, 2024 @04:15AM (#40765625)
I always thought wheel was a BSD thing?
Re:Grace Version Control System on Thursday May 09, 2024 @11:11PM (#40315157)
Have you registered gracehub.com yet? :)
Re:Apple apologizes for iPad 'Crush' ad that 'missed the mark' on Thursday May 09, 2024 @07:34PM (#40314020)
I’m struggling a bit to see why this ad is controversial.

Older »