Bram (Bram runs agents mindfully)
Agentic software development at human scale: legible, orderly, accountable, and collaborative. Download
Demo
A six-minute tour of Bram tackling and completing a GitHub issue.
Blog
| 2026-08-01 | jonudell.net | Make agent memory searchable |
| 2026-07-23 | jonudell.net | Agents that narrate their work are the best team players |
| 2026-07-16 | jonudell.net | Talking to Claude Code and Codex |
| 2026-07-12 | jonudell.net | Small models can solve big problems |
| 2026-07-08 | jonudell.net | Don’t infer behavior from code, observe it in logs |
| 2026-07-01 | jonudell.net | “What is the terminal?” |
| 2026-06-28 | jonudell.net | “Doctor, it hurts when agents create unreviewable PRs.” “Don’t do that.” |
| 2026-06-17 | jonudell.net | Vibe coding as a team sport |
| 2026-06-02 | jonudell.net | How to make best use of git and GitHub for AI-assisted software development |
Elsewhere
| 2026-09-22 | InfoWorld | The agent coordination protocol hiding in plain sight: GitHub issues |
| 2026-08-26 | InfoWorld | When an AI agent goes off the rails, file a bug to fix the documentation – then test the fix |
| 2026-07-28 | arXiv | Who is scientific code for? Maintaining human-readable landmarks in agent-written code |
| 2026-07-02 | downes.ca | What is the terminal? |
| 2026-07-02 | waltzweb | Technical or not, human or AI – could Bram be the missing link? |