Instructions for any AI agent working in this repo. The full repository guidelines live in CLAUDE.md; this file leads with the one thing that is easiest to get wrong: the experience bar. core/auth/gmail-credentials.json is an OAuth client for an installed application, and Hexis ships as a desktop app. Google documents that an installed app's client secret is not confidential, and RFC 8252 ("OAuth 2.0 for Native Apps") agrees — a native client cannot hold a secret, so nothing in the…
62310mo agoReviewMountCreate a free account to mount
Hexis is an edge-native memory system that gives AI persistent identity, continuity, and autonomy. Core thesis: LLMs are intelligence engines but lack selfhood. Hexis wraps any LLM with a PostgreSQL-backed cognitive architecture providing: Key principle: The database is the brain, not just storage. State and logic live in Postgres; Python is a thin convenience layer. A change is not "done" when it compiles or the test passes. It is done when the end-to-end experience holds. Check every user-facing change against…
62310mo agoReviewMountCreate a free account to mount
Weigh a hard decision with real tradeoffs — whether to take a deal, walk away, choose between options, or commit to something consequential — by deliberating it from several perspectives before acting
Connect Gmail through first-class guided setup, inspect status, complete authorization, queue read-only backfill, control jobs, and revoke local access
62310mo agoReviewMountCreate a free account to mount
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md or AGENTS.md?
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
What is a skill?
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Can I search my own team's files too?
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.