Founder and CEO of Oxagen
I build agents that ship on their own.
I'm Mac Anderson. I research coding agent best practices and build autonomous software developer agents. My work covers the agent software development lifecycle, code graphs, and ontologies for AI agents. I wrote code by hand for 16 years before I handed all of it to agents in 2026.
AI engineering blog
Coding agent research
My guides connect the research to the work of building and shipping software with AI agents.
- Coding agent best practices
Task scope, repository context, tests, review, and evidence before a merge.
- Agent software development lifecycle
How to build software with AI agents from a task brief through deployment and recovery.
- Claude Code practices
Repository instructions, tool permissions, hooks, and verification for Claude Code.
- Code graphs and vector search
Graph RAG for codebases, dependency retrieval, and graph databases for coding agents.
- Ontologies for coding agents
Types, relations, and checks for AI agent ontology graphs.
Activity
30,788 contributions in 245 days
Each dot is one day on GitHub. Before 26 February 2026, Mac wrote his code by hand. After it, agents wrote the code and he directed them, read their work, and decided what merged.
- Contributions in all of 2025
- 38Before agents wrote the code
- Contributions since 26 Feb 2026
- 30,788245 days
- Merged pull requests
- 8,144All time, every repository
- Most in one day
- 1,144August 30, 2026
- Longest daily streak
- 74Days in a row
- Active days in the last year
- 231Out of 365
How these numbers are counted
- Contributions are GitHub's contribution calendar counts, which include private contributions Mac has chosen to show.
- The site reads GitHub again at most once a minute for the profile counts and the years from 2026 on, and about once an hour for the repositories and languages. Earlier years come from the last full sync.
- This total adds up every day from February 26, 2026, when agents began writing Mac's code, through today.
- Pull request and issue counts are all-time GitHub search results, which cover only the repositories macanderson's token can see.
- The longest streak is the most days in a row with at least one contribution each.
Books
Books
Guide
How to Own Intelligence
A step-by-step guide to building a data pipeline for fine-tuning large language models on your own data
17 chapters, 119 sources, 1 h 49 min to read
Field manual
How to Build Autonomous Coding Agents
Build the deterministic system around the model. Then operate the agents you run: identity, authority, budget, equipment, and a record another person can read.
21 parts, 27 sources, 1 h 39 min to read
Research
Latest research
- October 28, 2026Agent software development lifecycleHow to build software with AI agents: define the task, prepare context, implement, verify, review, deploy, and check the result in production.2 min
- October 28, 2026Claude Code software development best practicesClaude Code practices for shipping software: concise repository rules, scoped tools, repeatable checks, code review, and evidence tied to the final commit.3 min
- October 28, 2026Code graphs and vector search for codebasesGraph RAG for codebases: combine code graphs with vector search, retrieve callers and tests, and evaluate graph databases for coding agents.2 min
- October 28, 2026Coding agent best practicesMac Anderson's guide to coding agent best practices: task scope, code context, tests, review, and evidence before autonomous agents ship software.3 min
- October 28, 2026Ontologies for coding agentsOntologies for AI agents: define code entities, graph relations, constraints, and source evidence so coding agents can check the context they use.3 min
Work
Products
Company
Oxagen
Workforce management for autonomous agents. Each agent gets an identity, a mandate that sets what it may do and spend, the tools it needs, and a record of what it did.
Wraps Claude Code and Codex
Open source, Rust
Stella
A fast, model-agnostic terminal coding agent. Its definition of done is a witness test: one that fails on the old code and passes on the new.
58 of 89 on Terminal-Bench 2.1, against 44 for Claude Code on the same model
Benchmarks
Arena
Runs a coding agent head to head against Claude Code, Gemini, and other agents, with regression checks that keep it improving instead of drifting.
Rules published before each run
Open specification
Context Graph Protocol
A typed graph format for an agent's context: how to represent it, exchange it, and account for every token of it.
SDKs for TypeScript, Python, and Go
For agents
Agent access
This site is written for AI agents as well as people. Point yours at it and it reads the same facts you do.
See the site blueprint- /llms.txt
A map of the whole site in the llms.txt format.
- /llms-full.txt
Every page in one markdown file.
- /manual/write-the-mandate.md
Any page as markdown. Add .md to the address.
- /mcp
A read-only MCP server with search and page tools.
Add the MCP server to Claude Code:
claude mcp add --transport http macanderson https://macanderson.com/mcp
Subscribe
Updates by email
New research, field manual updates, and the first episodes of Mac's video series go to subscribers first.