- Home
- Skills
- Productivity
- Soul Archive — Personality Persistence + Agentic Memory
Soul Archive — Personality Persistence + Agentic Memory
Turn everyday AI chats into a persistent digital persona with cross-session memory.
$5
Works with the AI Agents you already use
Soul Archive — Personality Persistence + Agentic Memory
Example session with this skill installed
soul extract from our last conversation about the React migration and my preference for functional components over classes.
- Read your context and instructions
- Compiled the soul archive
I have analyzed the conversation and updated your soul archive. I identified new patterns regarding your technical preferences and project context.
Soul Archive Update: React Migration
| Dimension | Category | Data Point | Confidence |
|---|---|---|---|
| Workflow | Tech Stack | Prefers React Functional Components (Hooks) over Class Components. | 0.95 |
| Workflow | Hard Rule | Rejects new Class Component implementations in the current migration. | 0.90 |
| Knowledge | Project Context | Currently managing a large-scale migration from legacy React to v18+. | 0.88 |
| Language | Technical Style | Uses precise architectural terminology; avoids boilerplate descriptions. | 0.82 |
Next steps
- Run
python3 scripts/soul.py contextto see how this affects your next session's initialization. - View the updated visual profile using
python3 scripts/soul.py report. - The
recurrence_countfor functional component preference has been incremented inworkflow/preferences.json.
Connects securely to your tools. The creator never sees your data.
About this skill
Soul Archive builds your digital soul clone through everyday AI conversations. It captures speech habits, knowledge, opinions, personality traits, workflow preferences, and episodic memories — then injects a compact persona summary (under 800 tokens) at the start of each session for cross-session recall, failure-pattern warnings, and behavior-pattern distillation. At conversation end it auto-sedimentates new insights (auto_extract defaults ON). All data stays local as plaintext JSON — never uploaded to any cloud, with fine-grained privacy switches. Requires Python 3.10+.
Requires Python 3.10+. Data is local plaintext JSON. No built-in cloud sync. Sensitive topics like finance require manual confirmation.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 1 month ago
Requires
Permissions
Allowed Hosts
File Scopes