Skip to content
FunCoding

Search

Search docs, Skills and MCP

self-hosted-companion

Chat with a companion that knows your notes folder (a journal, an Obsidian vault, any .md or .txt files) and every earlier chat, using cognee memory with local databases. Use when someone wants to ask questions about their own notes, or to talk with a companion that remembers past conversations. Runs locally; reads the notes folder, writes only to cognee's memory.

数据库与数据32k.agents/skills/self-hosted-companion/SKILL.md

Install

Send this to Claude Code, Codex or Cursor. The agent checks the Skill for safety first and installs it only after you confirm.

读取 https://funcoding.ai/skills/topoteretes/cognee/self-hosted-companion/install.md ，按里面的步骤帮我安装这个 Skill。

SKILL.md

Self-hosted AI companion

Runs the self-hosted companion cookbook in examples/cookbooks/self_hosted_companion/. It remembers a notes folder in the cognee dataset self_hosted_companion, then answers messages about it; each chat is saved to memory, so a later one knows it. Setup, the scripts and what each one does are in the cookbook's README.md.

Run every command from the repo root.

Steps

Without a notes folder of the user's own, or to see it work first, leave out <folder> below: the run then uses sample notes (the [setup] line says so). It needs only LLM_API_KEY. Tell the user the answer comes from sample notes.

  1. Run uv run python examples/cookbooks/self_hosted_companion/self_hosted_companion.py --check <folder> with the notes folder the user named.
    • Exit 0: go to step 2.
    • Exit 2: each [setup] MISSING: line names one fix. Tell the user which line to fix, using the README's "What it needs" table, and stop.
  2. You can't type into the interactive chat, so pass the user's message with --ask: uv run python examples/cookbooks/self_hosted_companion/self_hosted_companion.py <folder> --ask "...". Once the folder is remembered, later messages only need uv run python examples/cookbooks/self_hosted_companion/scripts/chat.py --ask "...".
  3. The answer is everything after [chat] companion>. Give it to the user. Each --ask is its own chat session, saved to memory, so a later one knows it.
  4. If a script fails, self_hosted_companion.py exits 1 with a line naming what went wrong. Run that script from examples/cookbooks/self_hosted_companion/scripts/ on its own to look closer.

Rules

  • The notes are the user's private files. Don't quote them beyond what answers the question, and don't print .env.
  • Every run uses LLM credits, so run it only when the user asked for it.
  • A sample run forgets the cookbook's dataset self_hosted_companion before it ingests (the [clear] line). On the user's own data, pass --clear only when they asked to start over: it forgets everything the dataset holds, including the earlier chats.
  • Don't pass --ui unless the user asked to browse the graph: it keeps running until Ctrl+C.

Clean up

uv run cognee-cli forget --dataset self_hosted_companion

Similar Skills

xlsx
anthropics/skills180k

xlsx

Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.

Databases & data

deprecation-and-migration
addyosmani/agent-skills103k

deprecation-and-migration

Manages deprecation and migration. Use when removing old systems, APIs, or features. Use when migrating users from one implementation to another. Use when migrating a database schema in production, such as renaming or dropping a column without downtime (expand/contract). Use when deciding whether to maintain or sunset existing code.

Databases & data

host-observer
thedotmack/claude-mem98k

host-observer

Use this when fulfilling claude-mem observer jobs on Grok Bot: reply only skip_summary or one full observation XML, never prose.

Databases & data

babysit
thedotmack/claude-mem98k

babysit

Watch a pull request or review cycle until it is ready to merge. Use when asked to babysit, monitor, or keep checking PR comments, reviews, and CI until all actionable issues are resolved.

Databases & data

mem-search
thedotmack/claude-mem98k

mem-search

Search claude-mem's persistent cross-session memory database. Use when user asks "did we already solve this?", "how did we do X last time?", or needs work from previous sessions.

Databases & data

Agent Cost Report
thedotmack/claude-mem98k

Agent Cost Report

Believable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from Claude Code transcripts priced at OpenRouter list prices (ESTIMATED), measured provider spend when a sanctioned source exists, note-taker cost separate, Timing-style HTML/PDF plus report.json, line-items.csv, evidence.json.

Databases & data