{"id":42894299,"url":"https://github.com/kbanc85/claudia","last_synced_at":"2026-03-16T02:52:14.299Z","repository":{"id":334393293,"uuid":"1140897918","full_name":"kbanc85/claudia","owner":"kbanc85","description":"Terminal-based AI chief of staff. Remembers relationships, tracks commitments, helps you think strategically. Runs on Claude Code.","archived":false,"fork":false,"pushed_at":"2026-02-24T18:51:08.000Z","size":3175,"stargazers_count":59,"open_issues_count":0,"forks_count":5,"subscribers_count":2,"default_branch":"main","last_synced_at":"2026-02-24T22:52:32.562Z","etag":null,"topics":["ai-assistant","claude-code","productivity","relationship-management","terminal"],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/kbanc85.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":"SECURITY.md","support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":"NOTICE","maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-01-23T22:38:14.000Z","updated_at":"2026-02-24T22:32:19.000Z","dependencies_parsed_at":"2026-02-08T05:01:21.967Z","dependency_job_id":null,"html_url":"https://github.com/kbanc85/claudia","commit_stats":null,"previous_names":["kbanc85/claudia"],"tags_count":76,"template":false,"template_full_name":null,"purl":"pkg:github/kbanc85/claudia","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kbanc85%2Fclaudia","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kbanc85%2Fclaudia/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kbanc85%2Fclaudia/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kbanc85%2Fclaudia/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/kbanc85","download_url":"https://codeload.github.com/kbanc85/claudia/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kbanc85%2Fclaudia/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29833637,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-25T17:57:15.019Z","status":"ssl_error","status_checked_at":"2026-02-25T17:56:11.472Z","response_time":61,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai-assistant","claude-code","productivity","relationship-management","terminal"],"created_at":"2026-01-30T15:03:15.216Z","updated_at":"2026-03-16T02:52:14.280Z","avatar_url":"https://github.com/kbanc85.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cp align=\"center\"\u003e\n\u003cimg src=\"assets/claudia-banner.gif\" alt=\"Claudia\" width=\"500\"\u003e\n\u003c/p\u003e\n\n\u003ch3 align=\"center\"\u003eA thinking partner who tracks relationships, not just tasks.\u003c/h3\u003e\n\n\u003cp align=\"center\"\u003e\nRemembers your people. Catches your commitments. Learns how you work.\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"https://github.com/kbanc85/claudia/stargazers\"\u003e\u003cimg src=\"https://img.shields.io/github/stars/kbanc85/claudia?style=flat-square\" alt=\"GitHub stars\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://www.npmjs.com/package/get-claudia\"\u003e\u003cimg src=\"https://img.shields.io/npm/v/get-claudia?style=flat-square\" alt=\"npm version\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://github.com/kbanc85/claudia/blob/main/LICENSE\"\u003e\u003cimg src=\"https://img.shields.io/badge/license-Apache%202.0-blue?style=flat-square\" alt=\"License\"\u003e\u003c/a\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n\u003ca href=\"#quick-start\"\u003e\u003cstrong\u003eInstall\u003c/strong\u003e\u003c/a\u003e ·\n\u003ca href=\"#what-makes-claudia-different\"\u003eWhy Claudia\u003c/a\u003e ·\n\u003ca href=\"#how-her-mind-works\"\u003eHer Mind\u003c/a\u003e ·\n\u003ca href=\"#integrations\"\u003eIntegrations\u003c/a\u003e ·\n\u003ca href=\"#how-it-works\"\u003eHow It Works\u003c/a\u003e\n\u003c/p\u003e\n\n---\n\n## The Problem With AI Assistants\n\nYou tell ChatGPT about Sarah on Monday. By Wednesday, it's forgotten.\n\nYou make a promise in a meeting. Nobody tracks it. You promise a deliverable on Friday and lose track of it by Wednesday. You meet someone important, and three weeks later you can't remember what you talked about.\n\n**AI tools don't have memory. Claudia does.**\n\n---\n\n## What Makes Claudia Different\n\n\u003ctable\u003e\n\u003ctr\u003e\n\u003ctd width=\"33%\" align=\"center\"\u003e\n\u003ch3\u003e🎯 Catches Commitments\u003c/h3\u003e\n\u003cp\u003eSay \"I'll send that by Friday\" and she tracks it. On Friday morning, she reminds you.\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"33%\" align=\"center\"\u003e\n\u003ch3\u003e🔗 Knows Your People\u003c/h3\u003e\n\u003cp\u003eEvery person she meets gets a living profile: relationship health, contact trends, connected entities. Ask about anyone and she has the full picture.\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"33%\" align=\"center\"\u003e\n\u003ch3\u003e⚖️ Learns Your Judgment\u003c/h3\u003e\n\u003cp\u003eTell her \"revenue work beats internal cleanup\" once. She writes it down and applies it across sessions: briefs, triage, delegation, risk surfacing.\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"33%\" align=\"center\"\u003e\n\u003ch3\u003e⚠️ Spots Patterns You Miss\u003c/h3\u003e\n\u003cp\u003eOvercommitting again? A key relationship going cold? The same mistake twice? She sees it forming and speaks up.\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"33%\" align=\"center\"\u003e\n\u003ch3\u003e🧠 Second Brain in Obsidian\u003c/h3\u003e\n\u003cp\u003eMemory syncs to an Obsidian vault organized with PARA: Active projects, Relationships, Reference, Archive. Graph view maps your world. Plain markdown you own forever.\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"33%\" align=\"center\"\u003e\n\u003ch3\u003e👥 Agent Team\u003c/h3\u003e\n\u003cp\u003eA two-tier team works behind the scenes. Fast Haiku workers handle document processing, while a Sonnet research scout tackles deep research with full autonomy.\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"33%\" align=\"center\"\u003e\n\u003ch3\u003e🌙 Learns in the Background\u003c/h3\u003e\n\u003cp\u003eOvernight, old memories fade, near-duplicates merge, and patterns surface. Each morning she knows a little more than yesterday.\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"33%\" align=\"center\"\u003e\n\u003ch3\u003e📄 Shows Her Sources\u003c/h3\u003e\n\u003cp\u003eEvery fact traces to its source. Ask \"how do you know that?\" and she shows the receipt.\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"33%\" align=\"center\"\u003e\n\u003ch3\u003e🪞 Session Reflections\u003c/h3\u003e\n\u003cp\u003eEnd a session with \u003ccode\u003e/meditate\u003c/code\u003e and she extracts what she learned: your preferences, patterns, and judgment calls. Next session, she's sharper.\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/table\u003e\n\n---\n\n## How Her Mind Works\n\n\u003ctable\u003e\n\u003ctr\u003e\n\u003ctd width=\"50%\" align=\"center\"\u003e\n\u003ch3\u003e💾 Remember\u003c/h3\u003e\n\u003cp\u003eEvery fact is stored with who said it, when, and how confident she is. Embeddings capture \u003cem\u003emeaning\u003c/em\u003e, not just keywords, so \"we pushed the launch\" and \"timeline shifted\" connect naturally.\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"50%\" align=\"center\"\u003e\n\u003ch3\u003e🔍 Recall\u003c/h3\u003e\n\u003cp\u003eSearch blends meaning similarity, importance, recency, and full-text matching. Accessing a memory strengthens it, just like the rehearsal effect in human cognition.\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"50%\" align=\"center\"\u003e\n\u003ch3\u003e🌙 Consolidate\u003c/h3\u003e\n\u003cp\u003eOvernight background jobs fade old memories, merge near-duplicates, and surface patterns: cooling relationships, overdue commitments, repeated behaviors. She wakes up sharper.\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"50%\" align=\"center\"\u003e\n\u003ch3\u003e📓 Vault\u003c/h3\u003e\n\u003cp\u003eMemory syncs to an Obsidian vault organized with PARA: Active projects, Relationships, Reference material, Archive. Graph view shows how your world connects. Plain markdown you own forever.\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/table\u003e\n\n---\n\n## Quick Start\n\n**1. Install**\n```bash\nnpx get-claudia\n```\n\n**2. Start**\n```bash\ncd claudia\nclaude\n```\n\n**3. Say hi.** She'll introduce herself, learn about you through a natural conversation, and generate a personalized workspace.\n\n\u003cp align=\"center\"\u003e\n\u003cimg src=\"assets/claudia-install.gif\" alt=\"Installing Claudia\" width=\"600\"\u003e\n\u003c/p\u003e\n\n**What's next:**\n- `/morning-brief` to see what needs attention\n- Tell her about a person and she'll create a relationship file\n- Share meeting notes and she'll extract action items\n- `npx get-claudia google` to connect Gmail, Calendar, Drive, and more\n\n**Requirements:** [Claude Code](https://docs.anthropic.com/en/docs/claude-code), Node.js 18+, Python 3.10+ (for memory), [Ollama](https://ollama.com) (for embeddings)\n\n\u003e **Embeddings model:** After installing Ollama, pull the required model: `ollama pull all-minilm:l6-v2`\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cstrong\u003eTemplate-only install (no memory system)\u003c/strong\u003e\u003c/summary\u003e\n\n```bash\nnpx get-claudia my-project --no-memory\n```\n\nInstalls only the template layer (skills, commands, rules). Claudia works using markdown files without semantic search or pattern detection. You can add the memory system later by running the installer again without `--no-memory`.\n\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cstrong\u003eUpgrading or fixing a broken install?\u003c/strong\u003e\u003c/summary\u003e\n\n```bash\ncd your-claudia-directory\nnpx get-claudia .\n```\n\nThis upgrades framework files (CLAUDE.md, skills, rules, daemon code) while preserving your data (context/, people/, projects/, databases). Safe to run multiple times. The installer detects existing installations and only updates system files.\n\n\u003c/details\u003e\n\n---\n\n## See It in Action\n\n\u003c!-- TODO: Replace with GIF showing memory recall --\u003e\n\n```\nYou:     What do I know about Sarah Chen?\n\nClaudia: Sarah Chen is CEO at Meridian Ventures. You met at SaaStr 2025.\n\n         📊 Relationship Health: Strong (last contact 3 days ago)\n\n         🎯 Open Commitments:\n         • Send updated pitch deck to Sarah [OVERDUE - was due Friday]\n\n         💡 Recent Context:\n         • She's interested in AI infrastructure angle\n         • Wants to see technical architecture doc\n         • Bringing in technical partner for next meeting\n\n         🔗 Connected to: Series A (project), Priya Sharma (introduced by)\n\n         Source: Call notes from Jan 28, Email thread Jan 30\n```\n\n**Morning brief pulls everything together:**\n\n```\nYou:     /morning-brief\n\nClaudia: ☀️ Morning Brief — Wednesday, Feb 19\n\n         ⚠️ Needs Attention:\n         • Send updated pitch deck to Sarah Chen [OVERDUE]\n         • Quarterly review with Acme Corp is tomorrow\n\n         👀 Watch:\n         • Haven't spoken to Marcus in 18 days (usually weekly)\n         • Two new commitments this week, zero closed\n\n         📊 Today: 3 meetings, 2 open commitments\n```\n\n**Judgment rules shape everything she does:**\n\n```\nYou:     I've got the Acme proposal and Marcus wants a catch-up.\n         Which first?\n\nClaudia: Acme proposal. Your judgment rules say revenue-generating\n         work beats relationship maintenance when there's a\n         deadline, and the Acme proposal is due Thursday.\n\n         I'll remind you about Marcus tomorrow morning.\n```\n\n**Pattern detection works across weeks, not just moments:**\n\n```\nClaudia: I've noticed something across the last few weeks.\n         You've taken on 4 new commitments without closing any.\n         Last time this happened (early January), two slipped\n         past deadline.\n\n         Want me to flag the lowest-priority ones so you can\n         decide what to defer?\n```\n\nEvery conversation builds on the last. She remembers.\n\n---\n\n## Who It's For\n\nClaudia detects your work style and generates structure that fits:\n\n| Role | What You Get |\n|------|--------------|\n| **Consultant** | Client folders, deliverable tracking, pipeline commands |\n| **Executive** | Direct reports, initiatives, board prep, leadership tools |\n| **Founder** | Investor CRM, fundraising cycles, team and product tracking |\n| **Solo Professional** | Flexible structure for wearing many hats |\n| **Creator** | Audience growth, content calendar, collaboration tracking |\n\n---\n\n## Key Commands\n\n| Command | What It Does |\n|---------|--------------|\n| `/morning-brief` | What needs attention today: commitments, meetings, warnings |\n| `/new-workspace [name]` | Spin up a new project workspace from templates |\n| `/meeting-prep [person]` | One-page briefing before a call |\n| `/capture-meeting` | Process notes into decisions, commitments, action items |\n| `/what-am-i-missing` | Surface risks, overdue items, cooling relationships |\n| `/research [topic]` | Deep research with web sources and memory integration |\n| `/inbox-check` | Lightweight inbox triage across connected email accounts |\n| `/brain` | Launch 3D brain visualizer |\n| `/meditate` | End-of-session reflection: extracts learnings, judgment, patterns |\n| `/deep-context [topic]` | Full-context deep analysis |\n| `/memory-audit` | See everything Claudia knows, with source chains |\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cstrong\u003eAll commands (41 skills)\u003c/strong\u003e\u003c/summary\u003e\n\n| Command | What It Does |\n|---------|--------------|\n| `/weekly-review` | Guided reflection across relationships and projects |\n| `/growth-check` | Periodic reflection on development, skills, and progress |\n| `/financial-snapshot` | Revenue, expenses, invoicing, and cash flow metrics |\n| `/draft-reply` | Email response drafts in your voice |\n| `/follow-up-draft [person]` | Post-meeting thank-you and summary |\n| `/new-person [name]` | Create a relationship file |\n| `/pipeline-review` | Active deals, capacity, pipeline health |\n| `/client-health` | Status across all client relationships |\n| `/databases` | View, switch, and manage memory databases |\n| `/brain-monitor` | Launch the Brain Monitor TUI dashboard |\n| `/fix-duplicates` | Find and merge duplicate entities |\n| `/memory-health` | Check memory system health |\n| `/diagnose` | Check memory daemon health and troubleshoot |\n\nPlus ~30 proactive skills (commitment detection, pattern recognition, judgment awareness, cognitive extraction, risk surfacing, and more) that activate automatically based on context.\n\n\u003c/details\u003e\n\n---\n\n## Brain Visualizer\n\nLaunch with `/brain` to see your memory as a 3D network graph. Entities are nodes, relationships are edges, and everything is interactive: click to inspect, filter by type, search by name.\n\n\u003cp align=\"center\"\u003e\n\u003cimg src=\"assets/brain-visualizer.png\" alt=\"Claudia Brain Visualizer\" width=\"700\"\u003e\n\u003c/p\u003e\n\n---\n\n## Integrations\n\nClaudia works fully on her own, but integrations let her see further.\n\n### Google Workspace\n\nConnect Gmail, Calendar, Drive, Docs, Sheets, Tasks, and more with a single setup command:\n\n```bash\nnpx get-claudia google\n```\n\nThis generates a one-click URL to enable all required Google APIs and walks you through OAuth setup. Three tiers available:\n\n| Tier | Tools | What You Get |\n|------|-------|-------------|\n| **Core** | 43 | Gmail, Calendar, Drive, Contacts |\n| **Extended** | 83 | Core + Docs, Sheets, Tasks, Chat |\n| **Complete** | 111 | Extended + Slides, Forms, Apps Script |\n\n### 500+ Apps via Rube\n\n[Rube](https://rube.app) (by Composio) connects Claudia to Slack, Notion, Jira, GitHub, Linear, HubSpot, Stripe, Figma, and hundreds more through one-click OAuth. No per-app MCP setup needed.\n\n| Category | Examples |\n|----------|----------|\n| **Communication** | Slack, Discord, Teams, Telegram |\n| **Project Management** | Jira, Linear, Asana, Trello, Monday.com |\n| **Knowledge \u0026 Docs** | Notion, Confluence, Google Docs, Coda |\n| **Code \u0026 Dev** | GitHub, GitLab, Bitbucket |\n| **CRM \u0026 Sales** | HubSpot, Salesforce, Pipedrive |\n| **And 500+ more** | [Browse the full list](https://rube.app) |\n\n### Obsidian Vault\n\nMemory auto-syncs to an Obsidian vault at `~/.claudia/vault/` using PARA structure. Every entity becomes a markdown note with `[[wikilinks]]`, so Obsidian's graph view maps your network. SQLite is the source of truth; the vault is a read-only projection you can browse and search.\n\n---\n\n## How It Works\n\n**41 skills · 33 MCP tools · 500+ tests**\n\nClaudia has two layers:\n\n**Template layer** (markdown) defines who she is. 41 skills, rules, and identity files that Claude reads on startup. Skills range from proactive behaviors (commitment detection, pattern recognition, judgment awareness) to user-invocable workflows (`/morning-brief`, `/research`, `/meditate`). Workspace templates let you spin up new projects with `/new-workspace [name]`.\n\n**Memory system** (Python) defines what she remembers. Two daemon modes share the same SQLite database:\n\n| Daemon | When | Purpose |\n|--------|------|---------|\n| **MCP daemon** | Per-session (stdio) | Serves ~33 memory tools to Claude Code |\n| **Standalone daemon** | 24/7 (LaunchAgent) | Runs scheduled jobs even when Claude Code is closed |\n\n| Scheduled Job | When | What It Does |\n|---------------|------|--------------|\n| Adaptive decay | 2 AM | Fades old memories, high-importance at half rate |\n| Consolidation | 3 AM | Merges duplicates, detects patterns, tracks relationships |\n| Vault sync | 3:15 AM | Syncs memory to Obsidian vault (PARA structure) |\n| Pattern detection | Every 6h | Surfaces trends across conversations |\n\n```\nYou ──► Claude Code ──► Reads Claudia's templates ──► Becomes Claudia\n                                                           │\n                                                    MCP daemon (stdio)\n                                                           │\n                                                           ▼\n                                                     SQLite + vectors\n                                                           ▲\n                                                           │\n                                              Standalone daemon (24/7)\n                                               ┌──────┼──────┐\n                                               ▼      ▼      ▼\n                                          Scheduler Ollama  Obsidian vault\n                                                           (PARA structure)\n```\n\n**Agent team for speed.** Claudia delegates structured work to a two-tier team. Tier 1 (Haiku): fast workers for document archiving, processing, and schedule analysis. Tier 2 (Sonnet): a research scout with independent context for multi-turn web research. Claudia keeps relationship judgment and strategy decisions for herself.\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cstrong\u003eTechnical deep dive\u003c/strong\u003e\u003c/summary\u003e\n\n**Semantic search** uses hybrid ranking: 50% vector similarity, 25% importance, 10% recency, 15% full-text. Accessing a memory boosts it (rehearsal effect).\n\n**Judgment layer** stores user-defined decision rules in `context/judgment.yaml`. Rules are extracted during `/meditate` reflections and applied by morning briefs, commitment detection, and risk surfacing. Claudia learns your priorities once and applies them consistently.\n\n**Document storage** keeps files, transcripts, emails on disk, linked to people and memories. Content-hash deduplication. Automatic lifecycle management.\n\n**Provenance chains** trace any fact to its source email, transcript, or conversation.\n\n**Graph traversal** connects dots across your network. Ask about one person, see related entities with top memories. The 3D brain visualizer (`/brain`) renders the graph in real-time.\n\n**Per-project isolation** keeps work memories separate from personal. Each workspace gets its own database.\n\n**Session reflections** (`/meditate`) extract learnings about your preferences, communication patterns, and judgment calls. These persist across sessions and make Claudia progressively sharper.\n\nFor full architecture diagrams, see [ARCHITECTURE.md](ARCHITECTURE.md).\n\n\u003c/details\u003e\n\n---\n\n## Privacy and Safety\n\n- **Fully local.** Memory, embeddings, cognitive tools run on your machine. No external APIs for storage.\n- **No external actions without approval.** Every email, calendar event, external action requires your explicit \"yes.\"\n- **Your data in two formats.** SQLite database (`~/.claudia/memory/`) for fast semantic search, plus a PARA-organized Obsidian vault for reading and graph navigation. Two independent copies you own forever.\n- **Delete anything, anytime.** Full control over your data. No lock-in, no cloud dependency.\n\n---\n\n## System Requirements\n\n| Component | Required | Purpose |\n|-----------|----------|---------|\n| [Claude Code](https://docs.anthropic.com/en/docs/claude-code) | Yes | Runtime |\n| Node.js 18+ | Yes | Installer |\n| Python 3.10-3.13 | Recommended | Memory system |\n| [Ollama](https://ollama.com) | Recommended | Embeddings + cognitive tools |\n\nWithout the memory system, Claudia still works using markdown files. With it, she gains semantic search, pattern detection, and relationship tracking.\n\n\u003e **Ollama model:** Run `ollama pull all-minilm:l6-v2` after installing Ollama. This is the embedding model used for semantic search.\n\n**Platforms:** macOS, Linux, Windows\n\n---\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cstrong\u003eTroubleshooting\u003c/strong\u003e\u003c/summary\u003e\n\n**Memory tools not appearing in Claude Code?**\n1. Check `.mcp.json` has a `claudia-memory` entry with the correct venv Python path\n2. Restart Claude Code in a NEW terminal\n3. Re-run the installer to fix paths: `npx get-claudia .`\n\n**Check standalone daemon health:**\n```bash\ncurl http://localhost:3848/status\nlaunchctl list | grep claudia\ntail -20 ~/.claudia/daemon-stderr.log\n```\n\n**Standalone daemon not running?**\n```bash\nlaunchctl load ~/Library/LaunchAgents/com.claudia.memory.plist\n```\n\n**Ollama not running after reboot?**\n```bash\nopen -a Ollama          # macOS\nollama serve            # Linux\n```\n\n**Pull models manually:**\n```bash\nollama pull all-minilm:l6-v2    # Embeddings (required)\n```\n\n**Google Workspace not working after enabling new APIs?**\nDelete the cached token and restart to re-authenticate with updated scopes:\n```bash\nrm ~/.workspace-mcp/token.json\n# Restart Claude Code\n```\n\n**Broken install? Re-run setup:**\n```bash\ncd your-claudia-directory\nnpx get-claudia .\n```\nThis updates daemon code, skills, and rules while preserving your databases and context files.\n\n\u003c/details\u003e\n\n---\n\n## Contributing\n\nClaudia is open source under the Apache 2.0 License.\n\n- **Template (skills, rules, identity):** `template-v2/`\n- **Memory daemon (Python):** `memory-daemon/` (tests: `cd memory-daemon \u0026\u0026 pytest tests/`)\n- **Installer:** `bin/index.js`\n- **Architecture:** [ARCHITECTURE.md](ARCHITECTURE.md)\n- **Dev guide:** [CLAUDE.md](CLAUDE.md)\n\n---\n\n## License\n\n[Apache License 2.0](LICENSE)\n\nOpen source. Free for personal and commercial use. Attribution required.\n\n---\n\n\u003cp align=\"center\"\u003e\nCreated by \u003ca href=\"https://github.com/kbanc85\"\u003eKamil Banc\u003c/a\u003e · \u003ca href=\"https://x.com/kamilbanc\"\u003e@kamilbanc\u003c/a\u003e · \u003ca href=\"https://aiadopters.club\"\u003eAI Adopters Club\u003c/a\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n\u003cem\u003e\"I learn how you work. Let's get started.\"\u003c/em\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\nIf Claudia helps you, a ⭐ on GitHub means a lot.\n\u003c/p\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkbanc85%2Fclaudia","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fkbanc85%2Fclaudia","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkbanc85%2Fclaudia/lists"}