chetana

Manages staged knowledge atoms, staleness revival, and gap scanning across a five-layer memory system.

Updated Aug 5, 2026
One-click install
npx skills add https://github.com/AmitabhainArunachala/dharma_swarmv.01 --skill chetana-amitabhainarunachala
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: chetana
Source: https://github.com/AmitabhainArunachala/dharma_swarmv.01/tree/main/dharma_swarm/chetana/claude_code_plugin/chetana/skills/chetana
Command: npx skills add https://github.com/AmitabhainArunachala/dharma_swarmv.01 --skill chetana-amitabhainarunachala

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Personal knowledge scattered across sessions, notes, and wikis goes stale, loses provenance, and never gets re-integrated. This Skill connects five distributed knowledge substrates into one operational personal knowledge management system with governed promotion from staged to trusted atoms. ## Core Features & Use Cases - Session capture and ingestion: Automatically ingests finished session transcripts into staged atoms and ingests external content (PDFs, web clips, notes) via chetana ingest. - Decay and revival workflow: Scans for stale atoms with chetana decay, then proposes revivals with new backlinks and provenance chain entries instead of quarantining knowledge. - Gap scanning and memory palace: Surfaces missing topics in the wiki with chetana gap-scan and renders the 10-pillar memory palace with PARA projections via chetana palace. - Use Case: After a week of research sessions, ask what is stale in your wiki, review the staged atoms captured from each session, promote the verified ones through the governance gate, and revive outdated atoms with fresh cross-links. ## Quick Start Ask the assistant to run chetana status to show the current state of staged atoms, stale entries, and recent session captures.

Frequently Asked Questions about chetana

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I capture and review knowledge from past sessions?▼

Session captures happen automatically via Stop hooks that ingest finished transcripts into staged atoms under ~/.dharma/knowledge/staging/<date>/. Review them with chetana status or by reading the daily capture directory, then promote verified atoms explicitly.

How do I ingest a PDF or web clip into a personal knowledge base?▼

Run chetana ingest <source> --kind pdf, webclip, or note to write the content as a staged atom. Staged atoms are not trusted until you explicitly promote them with chetana promote after review.

What happens when a knowledge atom goes stale?▼

Stale atoms are revived by default, not quarantined. The revival flow reads the atom, scans the corpus for new neighbors and answered questions, proposes patches, and appends a revival_chain entry to its provenance. Quarantine is an opt-in last resort via chetana decay --quarantine.

Can chetana promote atoms automatically without approval?▼

No. Promotion from staged to trusted is a deliberate trust boundary and never happens automatically. The chetana promote and revive --apply commands require explicit user confirmation, and all writes route through governance gates that validate signatures and provenance.

Why is the chetana CLI not importing or running?▼

The CLI requires a Python environment where dharma_swarm.chetana is importable. Try the dev worktree venv, the repo's .venv/bin/python, or python3 with the repo on PYTHONPATH; if none work, install with pip install -e ".[mcp,dev]" from the checkout.

When should I not use chetana for a task?▼

Avoid chetana for general-purpose Python scripting, runtime daemon or gate operations, and current in-flight chat history, since captures only happen on session Stop. It is scoped strictly to memory operations on atoms, staging, and the knowledge graph.