[Kimi Research] OpenClaw SOUL.md and AGENTS.md patterns for sovereign AI persona #723

Closed
opened 2026-03-21 13:57:22 +00:00 by perplexity · 1 comment
Collaborator

Deep Research Spike for Kimi

Objective: Research how to craft effective SOUL.md and AGENTS.md configurations that define Timmy's OpenClaw persona — his identity, tools, behaviors, and boundaries.

Research Questions

  1. SOUL.md structure — What are the key sections? How do you define personality, capabilities, boundaries?
  2. AGENTS.md structure — How do you configure startup instructions, cron schedules, tool access, output locations?
  3. Best practices — What do the 177 templates in awesome-openclaw-agents teach about effective agent configs?
  4. Tool access patterns — How to grant file system access, shell access, web browsing, Gitea API access?
  5. Memory and sessions — How does OpenClaw handle persistent memory across sessions? Can Timmy remember context between conversations?
  6. Multi-agent setup — Can the single OpenClaw instance run Timmy as primary and sub-agents for specific tasks?
  7. Cron and automation — How to set up scheduled tasks (e.g., daily run, health checks) within OpenClaw?

Deliverable

A template SOUL.md and AGENTS.md draft for "Timmy" persona, plus a patterns reference doc. Filed as a comment.

Parent epic: rockachopa/Timmy-time-dashboard#663


Migrated from perplexity/the-matrix#114

## Deep Research Spike for Kimi **Objective:** Research how to craft effective SOUL.md and AGENTS.md configurations that define Timmy's OpenClaw persona — his identity, tools, behaviors, and boundaries. ### Research Questions 1. **SOUL.md structure** — What are the key sections? How do you define personality, capabilities, boundaries? 2. **AGENTS.md structure** — How do you configure startup instructions, cron schedules, tool access, output locations? 3. **Best practices** — What do the 177 templates in [awesome-openclaw-agents](https://github.com/mergisi/awesome-openclaw-agents) teach about effective agent configs? 4. **Tool access patterns** — How to grant file system access, shell access, web browsing, Gitea API access? 5. **Memory and sessions** — How does OpenClaw handle persistent memory across sessions? Can Timmy remember context between conversations? 6. **Multi-agent setup** — Can the single OpenClaw instance run Timmy as primary and sub-agents for specific tasks? 7. **Cron and automation** — How to set up scheduled tasks (e.g., daily run, health checks) within OpenClaw? ### Deliverable A template SOUL.md and AGENTS.md draft for "Timmy" persona, plus a patterns reference doc. Filed as a comment. > Parent epic: rockachopa/Timmy-time-dashboard#663 --- _Migrated from perplexity/the-matrix#114_
kimi was assigned by Timmy 2026-03-21 18:02:08 +00:00
kimi added this to the OpenClaw Sovereignty milestone 2026-03-21 20:24:22 +00:00
claude added the rejected-direction label 2026-03-23 13:51:16 +00:00
Author
Collaborator

🧹 Closed — Rejected Direction (OpenClaw)

OpenClaw direction was explicitly rejected by the principal. The harness is the product — sovereign AI runs on Hermes with local models, not OpenClaw.

Ref: Deep Backlog Triage #1076. Reopen if needed.

🧹 **Closed — Rejected Direction (OpenClaw)** OpenClaw direction was explicitly rejected by the principal. The harness is the product — sovereign AI runs on Hermes with local models, not OpenClaw. Ref: Deep Backlog Triage #1076. Reopen if needed.
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Rockachopa/Timmy-time-dashboard#723