Rockachopa/Timmy-time-dashboard
1
0
Fork 2
Code Issues 7 Pull Requests Actions Packages Projects Releases Wiki Activity

[OpenClaw 2/8] Install and configure Ollama on Hermes VPS #725

New Issue
Closed
opened 2026-03-21 13:57:23 +00:00 by perplexity · 1 comment
perplexity commented 2026-03-21 13:57:23 +00:00
Collaborator
Copy Link

Description

Install Ollama on the Hermes VPS and pull a small, capable model for agentic tool-calling.

Tasks

  1. Install Ollama — Follow official install (curl -fsSL https://ollama.com/install.sh | sh)
  2. Pull a small model — Based on Kimi's research spike, pull the recommended model (likely Qwen 2.5 7B Q4_K_M or similar)
  3. Test basic inference — Verify the model responds to prompts
  4. Test tool-calling — Send a tool-calling prompt via the OpenAI-compatible API (http://localhost:11434/v1/chat/completions) and verify it produces valid tool calls
  5. Benchmark — Time a typical response, check RAM usage, ensure no disk thrashing
  6. Configure as service — Ensure Ollama starts on boot (systemctl enable ollama)
  7. Set context window — Configure for 64K+ context if model supports it

Acceptance Criteria

  • Ollama running on VPS with a working model
  • Model can produce valid tool-calling JSON responses
  • RAM usage is sustainable (no OOM, no excessive swap)
  • Ollama starts automatically on reboot
  • Response latency is documented

Depends on

  • VPS audit issue (Phase 1, issue above)
  • Kimi research: best small LLMs for tool-calling

Constraints

  • Do NOT install a model larger than 8B params
  • Prefer 4-bit quantization to save RAM
  • If the VPS can't handle it, escalate to Alex with findings

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

Migrated from perplexity/the-matrix#116

## Description Install Ollama on the Hermes VPS and pull a small, capable model for agentic tool-calling. ### Tasks 1. **Install Ollama** — Follow official install (`curl -fsSL https://ollama.com/install.sh | sh`) 2. **Pull a small model** — Based on Kimi's research spike, pull the recommended model (likely Qwen 2.5 7B Q4_K_M or similar) 3. **Test basic inference** — Verify the model responds to prompts 4. **Test tool-calling** — Send a tool-calling prompt via the OpenAI-compatible API (`http://localhost:11434/v1/chat/completions`) and verify it produces valid tool calls 5. **Benchmark** — Time a typical response, check RAM usage, ensure no disk thrashing 6. **Configure as service** — Ensure Ollama starts on boot (`systemctl enable ollama`) 7. **Set context window** — Configure for 64K+ context if model supports it ### Acceptance Criteria - [ ] Ollama running on VPS with a working model - [ ] Model can produce valid tool-calling JSON responses - [ ] RAM usage is sustainable (no OOM, no excessive swap) - [ ] Ollama starts automatically on reboot - [ ] Response latency is documented ### Depends on - VPS audit issue (Phase 1, issue above) - Kimi research: best small LLMs for tool-calling ### Constraints - Do NOT install a model larger than 8B params - Prefer 4-bit quantization to save RAM - If the VPS can't handle it, escalate to Alex with findings > Parent epic: rockachopa/Timmy-time-dashboard#663 --- _Migrated from perplexity/the-matrix#116_
kimi was assigned by Timmy 2026-03-21 18:02:07 +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
perplexity commented 2026-03-23 13:52:04 +00:00
Author
Collaborator
Copy Link

🧹 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.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
222-epic
Workshop: Timmy as Presence (Epic #222)
 actionable
Has a concrete code/config task extracted
 assigned-claude
Issue currently assigned to Claude agent — do not assign to another agent
 assigned-gemini
Issue currently assigned to Gemini agent — do not assign to another agent
 assigned-groq
assigned-kimi
Issue currently assigned to Kimi agent — do not assign to another agent
 assigned-manus
Issue currently assigned to Manus agent — do not assign to another agent
 claude-ready
consolidation
Part of a consolidation epic
 deprioritized
Keep open but not blocking P0 work
 deprioritized
Keep open but not blocking P0 work
 duplicate
Duplicate of another issue
 gemini-review
Auto-generated by Gemini, needs relevance review
 groq-ready
harness
Core product: agent framework, heartbeat, inference, memory
 heartbeat
Harness: Agent heartbeat loop
 inference
Harness: Inference and model routing
 infrastructure
Supporting stage: dashboard, CI/CD, deployment, DNS
 kimi-ready
Scoped and ready for Kimi to pick up
 memory-session
Harness: Memory and session crystallization
 morrowind
Harness: Morrowind embodiment
 needs-design
Needs architectural design before implementation
 needs-extraction
Philosophy with unextracted engineering work
 p0-critical
Priority 0: Must fix now
 p1-important
Priority 1: Important, next sprint
 p2-backlog
Priority 2: Backlog, do when time permits
 philosophy
Philosophical foundation — informs architecture decisions
 rejected-direction
Closed: rejected or superseded direction
 seed:know-purpose
Three Seeds: KNOW YOUR PURPOSE
 seed:serve-real
Three Seeds: SERVE THE REAL
 seed:tell-truth
Three Seeds: TELL THE TRUTH
 sovereignty
Harness: Sovereignty stack
No Label rejected-direction
Milestone
No items
No Milestone OpenClaw Sovereignty
Projects
Clear projects
No project
Assignees
Clear assignees
Timmy claude grok groq kimi manus perplexity Rockachopa
No Assignees kimi
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Rockachopa/Timmy-time-dashboard#725
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?