Apache Burr: Build reliable AI agents and applications

1. burr

   1 12 2,505 8.9 Python

   Build applications that make decisions (chatbots, agents, simulations, etc...). Monitor, trace, persist, and execute on your own infrastructure.

   

   I couldn't find an explicit reference for the naming, but for anyone wondering there is a Hamilton example: https://github.com/apache/burr/tree/main/examples/multi-agen...

2. AppSignal

   www.appsignal.com featured

   Monitoring that respects your time & budget. APM, error tracking, and dashboards for modern web apps. Ten-minute setup, transparent flat pricing, and support from engineers who actually use the product.

   

3. phoebe

   2 2 3 8.6 Python

   SRE incident-investigation finite state machine for LLM agents, served over MCP by Theodosia. The agent keeps the full Grafana toolset; the FSM gates the procedure (triage, diagnose, verify, conclude) and the audit trail, not the tools.

   

   I've been enjoying building agents with a framework I created called Theodosia. You define the workflow as a Burr state machine, mount it as an MCP server, and the agent can only take transitions the graph allows. Illegal moves get refused with the legal alternatives handed back. Every step and refusal goes into a hash-chained ledger. Covers the guardrails and audit trail part of what you're describing at least. https://github.com/msradam/theodosia

4. harness-sdk

   3 57 6,826 9.8 Python

   Build an agent harness and control it end-to-end. Open-source SDK for production AI agents in Python & TypeScript - any model, any cloud.

   

   How does this compare to https://strandsagents.com/ ? I'm interested in tools in this space, right now I'm not attached to one, but Bedrock + Serverless on Agent Core feels like the "easy guided path" though I don't like the platform lock-in

5. Apache

   4 115 4,050 9.8 C

   Mirror of Apache HTTP Server. Issues: http://issues.apache.org

   

   Wow, such a un-apache-y homepage I've ever seen, vs. the canonical one: https://httpd.apache.org/

6. jido

   5 4 1,794 9.4 Elixir

   🤖 Autonomous agent framework for Elixir. Built for distributed, autonomous behavior and dynamic workflows.

   

   I've been working with jido https://jido.run and would definitely recommend it

7. chat

   6 12 7 7.4 JavaScript

   Developer first chat app designed to help humans help AI (by gitsense)

   

   If you include the following:

   https://github.com/gitsense/chat/blob/main/base-state/analyz...

   In your chat with AI, include the above file and let it know what your requirements are and I create the analyzer and include it.

   My can also think of my tool as a AI data prep tool. So if you have a clear prompt the AI can review the file during analysis and remove all unnecessary code so the extracted metadata will the stripped text which you can use search against.

8. theodosia

   7 1 15 9.6 Python

   Put an AI agent on rails: mount a Burr state machine as an MCP server so the agent can only take the next allowed step, with every step recorded and replayable.

   

   I have enjoyed using this framework in my personal and work projects, having a reliable stateful workflow for AI models while getting free observability. I stitched a tool that allows mounting a Burr state machine as an MCP, giving agents a rail to follow, and no matter how complex the state machine gets the MCP tools are constrained to state machine navigation: https://github.com/msradam/theodosia

   I am currently working on skills-to-state-machine conversions, since a lot of popular skills out there are already written as phases for an AI model to follow, so it would be great to leverage the explicit functionality of Burr to make that more reliable. Thank you for this amazing project.

9. SaaSHub

   www.saashub.com featured

   SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives

   

10. sddw

    8 6 10 - Shell

    Spec Driven Development Workflow

    

11. fleet

    9 6 0 - Python

    Python supervisor for running coding agents in parallel (by sermakarevich)

    

12. smart-codex

    10 3 0 10.0 Rust

    Lightweight coding agent that runs in your terminal

    

    I haven't made any changes yet and I think the changes that I do make, they will want. I want to create a `/knowledge` slash command that can quickly tell me what the Agent currently knows so I determine if I need to "lobotomy surgery" to make it not know something or add what it needs.

    I created a new brain that help me find the answer and the AI response for your situation is:

    > Codex does not just need a /v1/responses endpoint. It needs an OpenAI Responses-compatible agent surface. Many providers implement enough Responses API for text streaming, but not enough for Codex’s tool-call loop and event mapping.

    I can understand why they might have done this for performance and/or lock-in and/or AI thinking reasons.

    I don't think I will create a translation layer, as that would be a sync nightmare, so based on what I found and what you said, it doesn't look like you can use other providers unless you introduce a proxy layer to translate things.

    I should also note, even if you have the translation layer, you might end up breaking harness capabilities.

    I am going to update

    https://github.com/gitsense/smart-codex

    to include the `codex-rust-navigation` brain that you can use to chat with AI about. And you will probably want to use it since `gpt-5.5` estimated that 25 - 50 files did not have to be read:

    > Roughly 300-500 files avoided, with a defensible lower bound around 25-50 files.

    This brain is designed specifically for rust files so you will need to use code-intent if you want to ask more documention/config questions.

13. codex

    11 187 104,688 10.0 Rust

    Lightweight coding agent that runs in your terminal

    

    You can absolutely do that by using subprocess.run, or use the codex sdk

    https://github.com/openai/codex/tree/main/sdk/python

Suggest a related project