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- ~78%
- fewer tokens on structural queries
- 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.
“Who references ContentType?” — asked of Django
tokens — and no way to know what the grep missed
tokens — all 64 references, with the count to prove it
~78% fewer tokens
Median across the 10 highest-degree symbols in each of four public repos (requests, FastAPI, Django, coding-os) for references and rename_plan, measured against what a competent agent actually does — grep, then read around the top matches. Not against reading every file, which is the comparison that produces a prettier number nobody believes.
Where it loses: a 3-hop blast radius costs more than reading on mid-size repos (−7% on FastAPI), and on a small repo bare grep beats it outright. The harness publishes those rows too, and it refuses to score an answer whose traversal was cut short.
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 & app) | Full | Full hook parity — Bash, file edits, MCP tool calls, prompt context, and session lifecycle all fire. Same gates, same enforcement. |
| 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.