Memory Ingest — Development skill for Claude Code
Process new raw content into the agent memory knowledge base.
How to install Memory Ingest
Installs to ~/.claude/skills/robinbril-infinite-agent-memory-memory-ingest/SKILL.md
mkdir -p ~/.claude/skills/robinbril-infinite-agent-memory-memory-ingest && curl -fsSL https://raw.githubusercontent.com/robinbril/infinite-agent-memory/HEAD/commands/memory-ingest.md -o ~/.claude/skills/robinbril-infinite-agent-memory-memory-ingest/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Memory Ingest does
name: memory-ingest description: Process new raw content into the agent memory knowledge base. Creates source/concept/entity pages, cross-links them, updates the index. Usage: /memory-ingest (processes content from the current conversation or from raw/ directory)
/memory-ingest
Process new content into the agent memory.
Usage
`/memory-ingest` - ingest content from the current conversation context or `/raw/` directory.
Steps
- Identify the content to ingest (pas
Alternatives in Development
- Om Intake — Process all unread meeting notes in work/meetings/ — reads each file, classifies content, routes to the right 4.6k ★
- Hive — Browser-native hive-mind for CLI coding agents — Claude Code, Codex, Gemini, and OpenCode collaborate as real 473 ★
- Obsidian Ingest — Ingest a source into the vault — the vault rewrites itself around new knowledge 277 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Ingest Resource
Process raw resources (conversations, transcripts, articles) and extract atomic notes
Competitor Backlink Scanner
Reads a competitor backlink export from Ahrefs, Semrush, Moz or Majestic, strips out the links you can never w
Concept Extraction
Skill for extracting atomic concepts from source material and creating well-structured concept pages
Foundry Ingest
Ingest raw material into the Foundry vault.
Ingest Source
Ingest a new raw source into WIKI_VRE with provenance and backlinks
Foundry Capture Notes
Capture notes from a designated Apple Notes folder into raw/clippings/ for /foundry-ingest to route.
Related Agents
Ingest Runner
Executes the fast and lean ingest pipeline (skills/ingest/SKILL.md) for exactly one source — Python-first Raw
Source Ingester
Dispatched by ingest-source or executing-research-plan. Reads ONE source PDF/text under a specific focus and p
Worker Source Fetcher
Fetches URLs or processes pasted content, applies privacy filter, saves to raw/ directory. Returns path for in