FEED

Benchmark results from an M5 Max Mac show that local LLMs running via Ollama and OpenCode — particularly the 35B Qwen 3.6 MoE model — are fast and reliable enough for bounded agentic tasks, though…

The governance you know is the governance you repeat.

Every company has this person. The engineer who every production change flows through because they're the only one who knows the constraints. If you're thinking about putting AI agents anywhere near…

Deming told us. We made the signature the proof and called it quality.

On May 30th I published v0.1 of a Databricks integration pack for Swamp. By the end of the same evening it was at v0.13. Fifteen models, 100% A on every release, every model end-to-end smoke-tested.…

A developer documents the environment-snapshot mechanism in the Hermes AI agent runtime that caused tool subprocesses to inherit stale API keys, and identifies /opt/data/home/.bash_profile as the…

What a development system looks like when you build it to keep yourself honest

A homelab engineer describes using an AI agent (Amp) alongside a declared Swamp model architecture to turn a Frigate disk-full alert into an automated, rate-aware notification that includes projected…

A developer used Claude Code to build an offline meeting transcription pipeline on the Swamp framework, combining mlx-whisper, pyannote diarization, and a local Ollama LLM to produce Granola-style…

The sovereign cloud movement is forcing a question the industry has been avoiding. When you have to move off a hyperscaler, the bottleneck isn't the new provider's APIs. It's how precisely you can…

A developer describes building ADW, a 10,000-line Ruby pipeline that automates code shipping against a production Rails monolith through phased AI agents, and explains a migration to improve…

AI agents are probabilistic. The same prompt doesn't always produce the same output. That's not a problem to avoid. It's a problem to engineer around. Typed schemas, validated execution,…

Drawing parallels with Linux packaging ecosystems, this post proposes a 'swamp forge' to make collaborative extension development the default rather than the heroic choice.

A sandbox that teaches swamp, managed by swamp

A candid account of navigating the swamp extension ecosystem, from forking a libvirt plugin to stalled PRs. Why the path of least resistance keeps winning over collaboration.

Results of my first day in the swamp

AI sucks at following instructions. It tries, but ultimately, it lets you down. Like a hyped up kid on too much addy with 17 different distractions, lets just say it tends to drift a little from your

Killing n8n: Migrating 11 Automation Flows to Swamp in One Day - killing-n8n.md

Curating my media library with swamp instead of letting it grow forever - curating-with-swamp.md

What changes when your agent can observe reality instead of reading your notes about it

I tweeted a twelve-point spec for what an agent-native cloud actually needs to look like. Vercel volunteered. Cloudflare's engineers got to work. Here's the test.

Day two with Swamp: I climbed out of the mud and actually read the docs on swamp.club — and the framework for giving AI agents typed, versioned, deterministic memory turned out to be rather brilliant.

Sequential pipelines assume humans waiting in sequence. Agents do not wait.

swamp extension quality checklist. GitHub Gist: instantly share code, notes, and snippets.

Agent state that follows you, then your team

High trust doesn't mean no guardrails. It means everyone understands the direction well enough to act independently within it. When you pair that with the right systems, every person on the team can…

Every codebase has the rearchitecture that never gets prioritised. We split ours into six parallel workstreams and shipped it in eight days, start to finish. The hard part wasn't speed. It was…

I've been using Swamp (https://swamp.club) quite a bit at $job recently, and have been running into a pattern that I feel is useful enough to share.

How Larry Wall's virtues of a Perl programmer inspire me in this era of engineering

Adaptive building blocks are how automation keeps up with AI development