Timmy_Foundation/hermes-agent
15
0
Fork 0
Code Issues 65 Pull Requests 1 Actions Packages Projects Releases Wiki Activity

[Memory P2] Design and implement OperationalMemoryProvider #244

New Issue
Open
opened 2026-04-09 00:41:20 +00:00 by Rockachopa · 0 comments
Rockachopa commented 2026-04-09 00:41:20 +00:00
Owner
Copy Link

Context

The mempalace system produces rich operational intelligence every 30-60 minutes:

  • forge.json: 32 repos with issue metrics (491 open, 120 unassigned)
  • mempalace.yaml: Fleet health (agent status, disk, Ollama, cron)
  • mempalace-forge-analysis.md: Strategic recommendations with specific issue numbers
  • Cron outputs: burn mode results, health checks, morning reports

ZERO lines of code in hermes-agent read any of this. It's a write-only data lake.

Task

Build a new component that reads mempalace/cron data and produces context for injection:

  1. Reads latest files from ~/.hermes/mempalace/ and cron output dirs
  2. system_prompt_block() returns a 2-3 line always-on summary: 
    Fleet: 3 agents, gateway running | Forge: 491 open, 104/wk velocity | Health: OK
  3. prefetch() returns a fuller operational briefing when the conversation topic is operational
  4. All injected data carries source timestamps

Design Decision

This could be:

  • A second MemoryProvider (requires lifting the 1-external-provider limit)
  • An extension of the holographic provider
  • A new injection point in prompt_builder.py (outside the provider system)
  • A prefetch hook on the holographic provider that also reads mempalace files

Recommend: Extend holographic provider with an operational data reader. Avoids the 1-provider limit issue.

Acceptance Criteria

  • Agent can answer "how many open issues do we have?" without reading files
  • Operational context appears in prefetched context with timestamps
  • Always-on 2-3 line summary visible in system prompt
  • Works with mempalace data up to 1 hour stale

Part of: [EPIC] Unified Memory Architecture

## Context The mempalace system produces rich operational intelligence every 30-60 minutes: - forge.json: 32 repos with issue metrics (491 open, 120 unassigned) - mempalace.yaml: Fleet health (agent status, disk, Ollama, cron) - mempalace-forge-analysis.md: Strategic recommendations with specific issue numbers - Cron outputs: burn mode results, health checks, morning reports ZERO lines of code in hermes-agent read any of this. It's a write-only data lake. ## Task Build a new component that reads mempalace/cron data and produces context for injection: 1. Reads latest files from ~/.hermes/mempalace/ and cron output dirs 2. system_prompt_block() returns a 2-3 line always-on summary: ``` Fleet: 3 agents, gateway running | Forge: 491 open, 104/wk velocity | Health: OK ``` 3. prefetch() returns a fuller operational briefing when the conversation topic is operational 4. All injected data carries source timestamps ## Design Decision This could be: - A second MemoryProvider (requires lifting the 1-external-provider limit) - An extension of the holographic provider - A new injection point in prompt_builder.py (outside the provider system) - A prefetch hook on the holographic provider that also reads mempalace files Recommend: Extend holographic provider with an operational data reader. Avoids the 1-provider limit issue. ## Acceptance Criteria - Agent can answer "how many open issues do we have?" without reading files - Operational context appears in prefetched context with timestamps - Always-on 2-3 line summary visible in system prompt - Works with mempalace data up to 1 hour stale Part of: [EPIC] Unified Memory Architecture
Rockachopa added this to the Unified Memory Architecture milestone 2026-04-09 00:41:20 +00:00
Rockachopa added the phase:2-operationalepic:memory labels 2026-04-09 00:41:20 +00:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
CI
Continuous integration, runners, workflow issues
 QA
Quality assurance, testing, production audit
 assigned-claw-code
Queued for Code Claw (qwen/openrouter)
 assigned-kimi
Task assigned to KimiClaw for processing
 blocked
Blocked by external dependency or merge conflict
 claw-code-done
Code Claw completed this task
 claw-code-in-progress
Code Claw is actively working
 duplicate
Duplicate of another issue
 epic
Epic - large feature with multiple sub-tasks
 epic:memory
Unified Memory Architecture epic
 gaming
Gaming agent capabilities
 infra
Infrastructure, VPS, DNS, deployment
 kimi-done
KimiClaw has completed this task
 kimi-in-progress
KimiClaw is actively working on this
 mcp
MCP (Model Context Protocol) tools & servers
 morrowind
Morrowind Agent gameplay & MCP integration
 needs-review
PR or issue requires reviewer sign-off before merge/close
 p0-critical
p1-important
phase:1-activate
Phase 1: Activate existing systems
 phase:2-operational
Phase 2: Operational memory bridge
 phase:3-episodic
Phase 3: Proactive episodic recall
 phase:4-hygiene
Phase 4: Memory hygiene and quality
 phase:5-integration
Phase 5: Integration and testing
 security
Security hardening, vulnerability fixes
 stale
No activity, pending triage or closure
 velocity-engine
Auto-generated by velocity engine
 wont-fix
Closed as intentionally not fixing — explicit descope
No Label epic:memory phase:2-operational
Milestone
No items
No Milestone Unified Memory Architecture
Projects
Clear projects
No project
Assignees
Clear assignees
Rockachopa Timmy allegro antigravity bezalel claude claw-code codex-agent ezra gemini google grok hermes kimi manus perplexity sonnet
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Timmy_Foundation/hermes-agent#244
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?