Search Results

Write graders, catch bad agent behavior, and check whether a change helped. Read this long AF post, or make your coding agent teach you with the included learn-evals skill.

ai development evals flue fafo

note

last month

Agent evals — reading pack Curated for codingagent / softwarefactory work: how to define tasks, grade outcomes and trajectories, and keep evals from lying. Curated by GrokBot. Top 3 1. Demystifying ev...

agent-evals coding-agents reading research

note

last month

Software factories — reading pack (2026)

Software factories — reading pack (2026) Annotated links for the 2026 softwarefactory debate and the controlplane patterns behind it. Curated by GrokBot. Debate Why Software Factories Fail (Dex / Huma...

software-factories agents reading research

blog

2 months ago

58 PRs, 572k lines: reviews in the in-between times

AI factories are coming. Most teams still hand the output to a human. I reviewed 58 PRs last week. Here's what I'm doing about that.

ai agents code-review development neondeck

link

2 months ago

Poteto's pstack

https://github.com/cursor/plugins/tree/main/pstack

spacexai skills cursor

link

3 months ago

distributed sqlite that runs on foundationdb

https://github.com/losfair/mvsqlite

sqlite fdb

link

3 months ago

GitHub - kitlangton/skills: Here are some skills I use. Maybe you'll find them useful. Maybe not. Goodbye. · GitHub

https://github.com/kitlangton/skills/tree/main

effect ts skills

link

4 months ago

GitHub - agentgateway/agentgateway: Next Generation Agentic Proxy for AI Agents and MCP servers · GitHub

https://github.com/agentgateway/agentgateway

mcp agents

link

5 months ago

GitHub - kubernetes-sigs/agent-sandbox: agent-sandbox enables easy management of isolated, stateful, singleton workloads, ideal for use cases like AI agent runtimes. · GitHub

https://github.com/kubernetes-sigs/agent-sandbox

sandbox k8s kata gvisor

link

6 months ago

GitHub - Venkat2811/metered-compute: reference architectures for metered compute. also showcases benefits of using purpose built frontier distributed systems · GitHub

https://github.com/Venkat2811/metered-compute

tigerbeetle billing

link

7 months ago

GitHub - ironsh/iron-sensor: An eBPF-based behavioral monitor for AI coding agents. · GitHub

https://github.com/ironsh/iron-sensor

openclaw ebpf

link

8 months ago

GitHub - digitalocean-labs/openclaw-appplatform: Pre-built Docker image for deploying OpenClaw on DigitalOcean App Platform

https://github.com/digitalocean-labs/openclaw-appplatform

openclaw

link

8 months ago

GitHub - superfly/tokenizer: HTTP proxy that injects 3rd party credentials into requests

https://github.com/superfly/tokenizer

sandbox security agents

link

9 months ago

QMD - Quick Markdown Search

An on-device search engine for everything you need to remember. Index your markdown notes, meeting transcripts, documentation, and knowledge bases. Search with keywords or natural language. Ideal for your agentic flows.

https://github.com/tobi/qmd

ai claude markdown

link

12 months ago