lolabot / brain
AGENTS.md8 starsChanged 43 days agoMITView on GitHub
Available agents in the mesh network. Last updated: YYYY-MM-DD
In this repository4 other files it gives its agents.
- file-processingSkill
- mail-handlerSkill
- pa-memory-delegationSkill
- pa-onboardingSkill
The file
Files
Agents Registry
Available agents in the mesh network.
Last updated: YYYY-MM-DD
Active Agents
| Agent ID | Name | Host | Capabilities | Status |
Agent Capabilities
<!-- CUSTOMIZE: Add agent capability blocks here. Example:
### agent-id (Agent Name)
- **Role:** Description
- **Can do:**
- Task coordination and prioritization
- Research (web, docs, code)
- File and folder management
- Browser automation
- GitHub operations (issues, PRs)
- Writing documentation, runbooks
- **Contact:** Direct (this session) or via Slack
-->Planned Agents
| Agent ID | Name | Purpose | Host | Status |
| Planned |
How to Delegate
# Send task to an agent
amp-send <agent-id> "Task: <description>"
# Request status report
amp-send <agent-id> "Status report: <task>"
# Check responses
amp-inboxDoes it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.