Browse / Software development / Second brain / agent-context-os
agent-context-os
conorbronsdon
Portable, evolving context and workflow layer that works across Claude Code, Codex, Hermes Agent, OpenClaw, Cursor, Devin and other compatible coding agents.
Open conorbronsdon/agent-context-os → On the boundary of the four rules.
agent-skillsagentsaiai-agentsai-contextai-memoryclaude-codecodexcontext-engineeringcontext-managementcursordeveloper-tools
Works with any agent
ships AGENTS.md, the cross-tool instruction file.
In its own words
All backed by Git.
A portable, evolving Git-backed context and workflow layer for coding agents. Claude Code, Codex, OpenClaw, and OpenCode are first-class; Hermes Agent, Cursor, and Devin adapters are experimental.
Chat history, project instructions, and copied prompts drift apart. Context OS puts the durable parts in plain Markdown: who you are, what you are working on, decisions already made, and the workflows you want an agent to follow.
Claude Code, Codex, OpenClaw, and OpenCode, plus the experimental Hermes, Cursor, and Devin adapters, read the same repository state. A deterministic lifecycle kernel turns reviewed setup, checkpoint, and close requests into hash-checked proposals and receipts, without treating native memory as the source of truth.
Context OS does not scrape every account, sync product UIs automatically, or install integrations on setup. Imports are selective, browser-project sync is manual, and external capabilities remain opt-in.
Experimental starter for one project
For a small project, try keeping the objective, decisions, and latest handoff in one instruction file. If separate notes help you review that context, the experimental three-file starter provides copyable instructions, current work, and a handoff. It needs a file-capable agent and manual review, with no installer or runtime registration.
The repository's own description, then 12% of its README. Read the rest on GitHub ↗
Read from the repository's git tree on 2026-08-17.