Your AI agent is brilliant.
It just forgets everything.
Coding OS is the cognitive operating system that gives AI coding agents memory, structure, and discipline — a knowledge graph, a task board, and an enforced engineering loop, on top of the agent you already use.
uv tool install coding-os && cos init- ≈ 98%
- fewer tokens
- 3
- cognitive layers
- 20+
- stack templates
Three failure modes. Three fixes.
Amnesia
Every session starts from zero. Yesterday's decisions are gone.
Cross-session memory: observations, learned patterns, and a session digest the next agent inherits.
Token burn
The agent greps and re-reads half the repo to answer one structural question.
A precomputed knowledge graph answers “who calls this / what breaks” in one query.
Chaos
It codes before it thinks, skips the plan, and claims “done” without running anything.
A complexity gate + Scrumban board + verification matrix, enforced by hooks — not vibes.
“What breaks if I change this function?”
tokens — grep, then read ~100 caller files
tokens — one graph query, full blast radius
≈ 98% fewer tokens
Honest asterisk: measured on this repo's own benchmark; exact numbers shift per machine and repo — the ratio is what holds.
One kernel, three brains
The Complexity Gate routes every request through a disciplined loop — and hooks enforce it, so the agent can't skip a step.
- Classify
- Orient
- Plan
- Execute
- Verify
graph_os
NavigateExtractors index code, docs, and configs into a queryable graph: callers, blast radius, contracts, rename plans.
thinking_os
RememberMemory, learning, and metrics. Sessions record observations; the next session starts with a digest, not amnesia.
board_os
PlanA Scrumban board with WIP limits, definition-of-ready, and lifecycle hooks. Tasks are contracts, not vibes.
Honest support matrix
“Agent-agnostic” is a design goal, not a marketing claim. Today two adapters ship: claude and codex.
| Runtime | Hook coverage | What that means |
|---|---|---|
| Claude Code | Full | Every hook fires — gates, skills, doc-anchors, and verification. The engineering loop is enforced end to end. |
| Codex CLI | Partial | Bash-event hooks fire; the core loop, board, and knowledge graph all work. Enforcement that needs non-Bash events is advisory. |
| Codex app | None | No hook runtime. The CLI and git-level commit hooks still enforce the commit contract on every commit. |
| Humans | Git hooks | Install the git hooks and the commit contract holds; the board and graph are agent-optional — ideal for mixed human/agent teams. |
Give your agent a memory it can't lose.
Stack templates ship playbooks, rules, and skills per framework. Install in one command and keep the agent you already use.