Memory & Skills

Cross-conversation memory

Tell it your name or preferences once; it remembers in every future chat.
Memory is plain Markdown under ~/Library/Application Support/Naseem — inspect or edit it anytime.

When a run hits friction — a denied action, a failure it recovered from, a guardrail — Naseem proposes a lesson; approved lessons quietly steer future runs.
Pending lessons appear as a banner below the chat; review, edit, or delete them in the Knowledge inspector's Lessons tab (auto-approve toggle in Settings → Integrations).

Naseem turns recurring multi-step tasks and corrected mistakes into reusable, keyword-triggered skills (via learn_skill, Pro).
Import skills or whole skill collections from URLs and repos — human-review gated.
Browse what it knows in the Knowledge inspector (memory / skills / tools).
Switch any skill on or off — every skill in the brain icon → Skills has a switch. Off keeps the file and its text but hides the skill from the model, so a run cannot pick it. Regular skills ship on.
Trial skills — a skill marked TRIAL ships switched off, because it changes how a run works. Turn it on per skill; it is offered to the model only after that.
Codebase review (trial) — hands the reading to sub-agents so the main model never loads the code: it sizes the job first, uses one reviewer for a small project and one per dimension for a large one, and each writes findings to a file under naseem/reviews/<date>/. Every finding is then re-checked against the cited lines and the ones that don't survive are thrown out, so you get a short list with file and line rather than a long plausible one. In approval mode it tells you the plan first — files, lines, how many reviewers, roughly how many calls — and asks whether you want the full review, reviewers without verification, or a quick single-pass look. In Autonomous mode it prints the plan and goes.