Pi: the coding agent behind my agent framework work
Pi is the TUI coding agent I run my multi-agent work through. Seven open-source extensions I built for it: delegation, monitors, fallback, cron, MCP, signals, keys.
[ Read more → ]rafal@arasz:~$ls blog/
Engineering notes, project updates, and technical deep-dives. [ RSS feed ]
ai-raccoon's Architecture Evolution: One Server, Any Model, Code Search
Five architectural changes from v1.6.0 to v1.33.2: proxy server, event pump, custom embeddings, code corpus, project identity.
[ Read more → ]What AI Agents Can Build: A Job-Search Assistant Where AI Writes the Code and Runs the Product
How AI agents built and power a full-stack job-search assistant — from CV tailoring to interview prep — and what that says about what's possible when agents write the code and AI runs the product.
[ Read more → ]Auditable Agent Decisions: Integrating Semantica with ai-raccoon and ai-badger
How combining Semantica's causal knowledge graph with ai-badger hooks and ai-raccoon's persistent vector+BM25 memory layer automates the creation and retrieval of auditable decision chains for AI coding agents.
[ Read more → ]AiRaccoon: An MCP Memory Server Where Measurement Beat the Plan
AiRaccoon is a local-first MCP memory server for AI agents: encrypted SQLite, hybrid FTS5+vec0 search, project and workspace isolation, cloud sync. Measured on 2026-08-04: 60% top-3 match rate on the 35-query baseline, 6/6 section hits on the structure-aware harness.
[ Read more → ]The Skills I Gave My Coding Agent
A tour of the skills my agent framework ships — what each one is for, what it actually does to your repo, and the situation that makes you reach for it. Starting with the one I open almost every day.
[ Read more → ]The Bill Said Delegate. So I Made It the Default.
Part 2 measured a month of AI agent costs. This is what I changed because of it: my agent framework now picks the right model for each job, refuses hand-offs that name no model, and has a new team-lead role whose only job is routing work.
[ Read more → ]What AI Coding Agents Actually Cost, Part 2: A Full Month of Data
Part 1 compared three agents over two weeks. Part 2 reads 24 days of ccusage data off one machine — $10,453 in API-equivalent estimates, 97.81% cache reads, and the kinds of sessions that actually raise the bill.
[ Read more → ]code-review-graph: When Your AI Agent Needs a Map of Your Codebase
A practical look at code-review-graph — how it builds a structural knowledge graph of your codebase, what it actually found in two real projects, and whether the token savings are real.
[ Read more → ]What AI Coding Agents Actually Cost: Real Usage Data Across 3 Agents
Data-driven comparison of Claude Code, Hermes Agent (via OpenRouter), and GitHub Copilot with real token usage, cost breakdowns, and the 80/20 strategy.
[ Read more → ]Hermes Agent: A Developer-First AI Agent with Deep Integration Hooks
A practical review of Hermes Agent — how it compares to Claude Code, its hook system for prompt customization, token-friendly skill design, and why it pairs well with ai-badger.
[ Read more → ]Introducing ai-badger: A Portable Agent Framework for the Multi-Agent Era
What ai-badger is, how the stack×feature catalog model works, and why portable agent knowledge matters when you run Claude Code, Hermes, Copilot, and Junie side by side.
[ Read more → ]