Hi Hacker News! Matvey, one of the authors, is here.While building enterprise agents, we ran into a problem: the more tools you connect to the AI, the higher the chance it will run out of control and leak sensitive data.Guardrails, in theory, should prevent this, but the situation is worrying: - Non-deterministic guardrails (LLM as a judge, auto modes, etc.) are vulnerable to prompt injections,...
Recently, OpenAI shipped "Sites", a mini-apps AI builder. It's similar to "Databricks Apps" or Loveable.
We worked on this concept for the last few months, and tried to approach it from the most "open source friendly" and interconnectable way, providing the ability to build mini apps re-using the MCP data layer, re-using MCP authentication while accessing those apps, and also exposing those apps as MCP servers themselves so they could be utilized through the 3'rd party clients like Claude Code.
We'd love for you to take a look at the repo, try it out, and give us your feedback!
We've recently decided to complicate life of AI bots in our repo https://archestra.ai/blog/only-responsible-ai, hoping they will just choose those AI startups who are easier to engage with.
Hi HN, Matvey, Ildar, Joey, and Dominik here.If you're building LLM agents that use tools, you're probably worried about prompt injection attacks that can hijack those tools. We were too, and found that solutions like prompt-based filtering or secondary "guard" LLMs can be unreliable.Our thesis is that agent security should be handled at the network level between the agent and the LLM, just...
For now, Archestra is categorizing tools and preventing the execution of tools that could leak data to the outside world without consent. Asking for permission for all tool calls may lead to fatigue; not asking for consent will expose the agent to the attack, so we're trying to strike a balance.
Local MCP servers are executables, and running straight from GitHub is quite dangerous. Also, to start the local MCP server and connect it to, for example, Gmail, one needs to register a Google Cloud account, issue a file with OAuth tokens, place it in a specific directory, and set the environment variable.
We built Archestra, a simple desktop orchestrator for open source MCP servers, enabling you to install and use self-hosted & remote MCP servers with just a few clicks. It's running local MCP servers in a Podman sandbox to prevent access to the host, dynamically adjusts the set of enabled tools, and maintains permanent memory. Most importantly, it handles authentication through the UI via OAuth or by retrieving API keys from the browser and launches MCP servers accordingly.
Archestra is open source and MIT: https://github.com/archestra-ai/archestra
A short demo, using GitHub, Gmail and Slack MCPs: https://www.loom.com/share/84ea6a684f014ebba5e39dd0dd0242a2
You can try it yourself by downloading the app and using it with local models, OpenAI, or some of our free tokens: https://archestra.ai.
Almost every tech company has private code—typically stored in private repositories. When working on Keep, we faced a decision: should we place certain code in the EE folder under a different license or keep it in a private repo, only sharing it with a small group of enterprise customers who explicitly requested it?
We chose to put that code on GitHub.
Ironically, putting more code in the GitHub repo made it appear "less open source," even though we could have simply hidden it, making the repo look like "clean OSS" as multiple companies do. For example, those who put their products without Web UI to the open source, build UI privately and serve the "full" version in the cloud.
While I understand (and share) the caution around licenses, I don’t think this concern applies to Keep. With 99% of our codebase under the MIT license, it’s a far cry from just having "parts of the code with an open source license."
I recommend running Keep locally and comparing the Open Source version to the playground where full version is running. You might find it challenging to spot the differences.
I also reccomend comparing Keep Open Source to BigPanda and Moogsoft. It may be surprising how much of it Keep OSS, real MIT-licensed Keep has.
Helm (https://github.com/grafana/oncall/tree/dev/helm/oncall), docker-composes for hobby and dev environments.
Besides deployment, there are two main priorities for OnCall architecture: 1) It should be as "default" as possible. No fancy tech, no hacking around 2) It should deliver notifications no matter what.
We chose the most "boring" (no offense Django community, that's a great quality for a framework) stack we know well: Django, Rabbit, Celery, MySQL, Redis. It's mature, reliable, and allows us to build a message bus-based pipeline with reliable and predictable migrations.
It's important for such a tool to be based on message bus because it should have no single point of failure. If worker will die, the other will pick up the task and deliver alert. If Slack will go down, you won't loose your data. It will continue delivering to other destinations and will deliver to Slack once it's up.
The architecture you see in the repo was live for 3+ years now. We were able to perform a few hundreds of data migrations without downtimes, had no major downtimes or data loss. So I'm pretty happy with this choice.
Matvey Kukuy, ex-CEO of Amixr and a head of the OnCall project here. We've been working hard for a few months to make this OSS release happen. I believe it should make incident response features (on-call rotations, escalations, multi-channel notifications) and best practices more accessible to the wider audience of SRE and DevOps engineers.
Hope someone will be able to finally sleep well at night being sure that OnCall will handle escalations and will alert the right person :)
Please join our community on a GitHub! The whole Grafana OnCall team is help you and to make this thing better.
Same time we've focused on making it useful for those who don't use Grafana for monitoring. Feel free to sign up in the Grafana Cloud and use just OnCall if you want.
We've already received multiple questions about OSS and on-premises. Will roll cloud version first, see how it works, collect feedback and build (and share) future plans!