local-llm-setup

Included with Lifetime

$97 forever

Use when the user wants to set up Ollama for SiftCoder, reduce token costs, or troubleshoot local-LLM drain/embedding issues. Covers install, model selection, env wiring, and verification.

AI Agents

What this skill does


# Setting up local LLM for SiftCoder

SiftCoder uses a cascade — **Ollama (local) → Anthropic API → MCP host sampling** — for both summarisation and embeddings. Local LLM cuts steady-state token cost by ~50× on repeat sessions.

## Install Ollama

```bash
# macOS
brew install ollama
brew services start ollama

# Linux
curl -fsSL https://ollama.com/install.sh | sh
systemctl --user enable --now ollama
```

## Pull recommended models

```bash
ollama pull nomic-embed-text   # 137M params, embeddings
ollama pull llama3.2:3b        # summarisation (small, fast)
# or, for higher quality:
ollama pull llama3.1:8b
```

## Verify

```bash
curl -s http://localhost:11434/api/tags | jq '.models[].name'
siftcoder setup       # writes ~/.siftcoder/config.json with detected backends
siftcoder status      # shows daemon health
```

## Override via env

```bash
export SIFTCODER_DRAIN_BACKEND=ollama
export SIFTCODER_EMBEDDER=ollama
export OLLAMA_HOST=http://localhost:11434
```

Or edit plugin `settings.json`:

```json
{
  "siftcoder": {
    "memory": { "drainBackend": "ollama", "embedder": "ollama" },
    "ollama": { "summarizeModel": "llama3.1:8b" }
  }
}
```

## Troubleshooting

- **Daemon not picking up Ollama:** restart `siftcoder stop && siftcoder start` — backend cascade is resolved at boot.
- **Drain confidence low → escalates to Sonnet:** small models (3b) often score under threshold. Switch to `llama3.1:8b` or raise threshold in settings.
- **Embedding dim mismatch:** if you change embedder mid-stream, run `siftcoder drain --reset-vectors`.
- **Windows + WSL:** Ollama on host is reachable from WSL via `http://host.docker.internal:11434`.

## When NOT to use local LLM

- One-shot critical reasoning (use Sonnet directly via Anthropic).
- Reranking final retrieval (Claude reranker is materially better; cost is small).

Files: 1

Size: 2.0 KB

Complexity: 6/100

Category: AI Agents

Source: https://github.com/ialameh/sift-coder/tree/main/skills/meta/local-llm-setup

Related in AI Agents

skill-development

Included

Comprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.

AI Agentsscripts

reprompter

Included

Transform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.

AI Agentsscripts

adaptive-compaction

Included

Adaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.

AI Agentsscripts

agent-skill-creator

Included

Create cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.

AI Agentsscripts

llm-wiki

Included

Use when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.

AI Agentsscripts

skill-master

Included

Agent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.

AI Agentsscripts