Rendered at 03:06:47 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
bmiedlar 33 minutes ago [-]
I've noticed on some of my own research and testing that even with caps some agents will work around the per-call time limit using background processes. Do your caps cover compute in the detached processes?
ferar 2 hours ago [-]
Do it uses the claude code harness (for example) or bypass it? I ask because of the subscription. thanks
miguelrios 42 minutes ago [-]
It supports Claude Agents' harness but their sub is still not supported. I am working on it. Same for Codex / ChatGPT.
mfrye0 6 hours ago [-]
Very cool. I was waiting for something like this to pop up.
Is it possible to be added as a data source? I see you're mostly pointing the agent to easy / publicly available sources like the UK.
We have ~200 government registrar integrations now and 500M entities in the system. We essentially have better coverage than OpenCorporates at this stage. https://savvyiq.ai
miguelrios 6 hours ago [-]
Do you have an MCP? I am adding our internal tool proxy which can be used to plug in any MCP into it.
mfrye0 6 hours ago [-]
Yeah, but it's out of date. About to replace it with a new version that has SSO support and other updated APIs. Will be available next week.
whirlwin 6 hours ago [-]
Would like to hear from everyone: How are you dealing with PRs in 2026? It's our biggest bottle neck.
We are considering looking into attestations, e.g. through the SLSA spec: https://slsa.dev/ to ensure build provenance and verification before it is deployed.
The core concept is to have a frontier or very smart model run as an agent first for N times. The model get tools, skills etc and instructions. It does the job. At the end it leaves a note (like a retro) explaining what it did and what it could have done better.
As the agent runs, it also writes workflows to do the parts of the job it knows it can do in a more deterministic way (based on previous nodes and thinking traces of other runs etc). We made a dsl for this that has routing, classification, code nodes, etc to build these workflows.
For repetitive tasks (which is our focus) we find that after ~100 cases, the agent most times just runs a workflow end to end instead of looping towards a solution. Workflows are cheap, so the job ends up being way cheaper than an agent in a good model.
2 hours ago [-]
Rinkesh2010rpp 7 hours ago [-]
Cool project, I myself have a similar autonomous agent, in python
At rinkesh2010rpp/sudarshana. But I liked your mission control. Will for sure take some inspiration.
Also, what I have is ability to find other agents on run time, running on Modal, and a safety layer that checks every actions taken by the agent.
and happy to talk more.
Thanks
miguelrios 7 hours ago [-]
Very cool. Feel free to borrow from us what's helpful and send feedback our way!
ghempton 5 hours ago [-]
If your team is using subscriptions, it is a lot more cost effective (and higher quality) to simply use a local orchestrator to automatically deal with PR reviews. We built https://github.com/codealong/codealong in part to help with this.
miguelrios 5 hours ago [-]
very cool. thanks for sharing!
jstummbillig 8 hours ago [-]
I think I'll need like at least another 3-4 months of new models before I can deal with AI UI/UX design.
embedding-shape 4 hours ago [-]
It hasn't gotten better since a year ago, I don't have high hopes. People need to get better at making smaller decisions and having more opinions, not just prompt "Create page for dashboard".
miguelrios 2 hours ago [-]
This is fair feedback. We spent a ton of time in the UI for our hosted product and the main website (agentrun.ai) but very little in the OSS console. We’re spending more time on this now and making it better.
Is it possible to be added as a data source? I see you're mostly pointing the agent to easy / publicly available sources like the UK.
We have ~200 government registrar integrations now and 500M entities in the system. We essentially have better coverage than OpenCorporates at this stage. https://savvyiq.ai
We are considering looking into attestations, e.g. through the SLSA spec: https://slsa.dev/ to ensure build provenance and verification before it is deployed.
https://agentrun.ai/docs/self-improvement
https://agentrun.ai/docs/learning-reference
The core concept is to have a frontier or very smart model run as an agent first for N times. The model get tools, skills etc and instructions. It does the job. At the end it leaves a note (like a retro) explaining what it did and what it could have done better.
As the agent runs, it also writes workflows to do the parts of the job it knows it can do in a more deterministic way (based on previous nodes and thinking traces of other runs etc). We made a dsl for this that has routing, classification, code nodes, etc to build these workflows.
For repetitive tasks (which is our focus) we find that after ~100 cases, the agent most times just runs a workflow end to end instead of looping towards a solution. Workflows are cheap, so the job ends up being way cheaper than an agent in a good model.
Also, what I have is ability to find other agents on run time, running on Modal, and a safety layer that checks every actions taken by the agent.
and happy to talk more.
Thanks