Fixes inside open source agent platforms

Agent platforms break in the seams between the controller, the agent runtime and the model provider. I fixed those seams in four open source projects, each with a test that fails on the main branch.

A run of clear glass tubes on black steel stands. One joint is rejoined by a machined steel coupling, and a thin orange liquid flows through the repaired joint without a break.
5Pull requests merged in Sympozium in one week
238Worker tests green on my UniFi MCP branch, run by the maintainer
67,469GitHub stars on AnythingLLM
Year
2026
Sector
Agent systems
Client
Sympozium, AgentField, UniFi MCP, AnythingLLM
Duration
Open source, 2026
Stack
Go, Kubernetes, TypeScript, Node.js
Role
Contributor
Updated

The problem

On Sympozium, agent pods kept a fixed 1Gi memory limit whatever the runtime declared, so larger agents were killed for memory. The MCP server resource always showed 0 tools, and a rejected schedule retried every 30 seconds with nothing on its status.

On AgentField, legacy requests sent an execution ID to the agent but never wrote the execution row, so status updates got a 404. On UniFi MCP, a relay that registered again kept receiving traffic on its dead WebSocket.

What I built

Reproduced each bug on the main branch and added a regression test with each fix. Two maintainers confirmed the tests fail on main and pass on my branch.

Sympozium, a Kubernetes controller for AI agents in Go. Carried the runtime resources onto the agent pod, filled the MCP tool status through the MCP bridge, stopped the retry loop on admission denials and made the utility images configurable for air-gapped clusters.

AgentField control plane in Go. Wrote the execution row before the legacy handlers reach the agent and copied the final status onto it. After review I kept HTTP 202 replies non-terminal, so background reasoners are not marked done too early.

UniFi MCP on Cloudflare Workers and Durable Objects. Kept the relay bound to the newest socket across rebuilds, with three lifecycle tests.

AnythingLLM collector in Node.js. Fixed the URL check that read YouTube channel links as single videos, with a test file of real links.

How the work ran

Each fix went through public review in its pull request. The AgentField fix changed after the first review, and the merged version includes that rework.

Result

5 pull requests merged in Sympozium in one week.

The AgentField fix merged with 683 lines added and 20 removed across 4 files.

The UniFi MCP maintainer reproduced the bug in the real Workers runtime and ran the full suite of 238 tests green on my branch.

The AnythingLLM fix merged into a project with 67,469 GitHub stars.

“Nice, a schedule spinning every 30s with nothing on its status is exactly the kind of thing that's miserable to debug.”

Sympozium maintainer, in the review of PR 665, on GitHub

These projects are public, so they are named. Every number links to the pull request or the repository.

[+]More case studies

More case studies

All case studies

Next step

If an agent or LLM feature breaks in production, send me a written brief.

Start a brief

I reply in writing within one working day.

How it starts

  1. [1]Send a written brief
  2. [2]Sign the agreement
  3. [3]Week 1 starts