RAGLite - Local Expandable Library AI Library
by @virajsanghvi1
Local-first RAG cache: distill docs into structured Markdown, then index/query with Chroma + hybrid search (vector + keyword).
clawhub install raglite-libraryπ About This Skill
name: raglite version: 1.0.0 description: "Local-first RAG cache: distill docs into structured Markdown, then index/query with Chroma + hybrid search (vector + keyword)." metadata: { "openclaw": { "emoji": "π", "os": ["darwin", "linux"], "requires": { "bins": ["python3", "pip"] } } }
RAGLite β a local RAG cache (not a memory replacement)
RAGLite is a local-first RAG cache.
It does not replace model memory or chat context. It gives your agent a durable place to store and retrieve information the model wasnβt trained on β especially useful for local/private knowledge (school work, personal notes, medical records, internal runbooks).
Why itβs better than βpaid RAGβ / knowledge bases (for many use cases)
If you later outgrow local, you can swap in a hosted DB β but you often donβt need to.
What it does
1) Condense βοΈ
Turns docs into structured Markdown outputs (low fluff, more βwhat mattersβ).2) Index π§
Embeds the distilled outputs into a Chroma collection (one DB, many collections).3) Query π
Hybrid retrieval:rg)Default engine
This skill defaults to OpenClaw π¦ for condensation unless you pass --engine explicitly.
Prereqs
http://127.0.0.1:8100)
rg installed (brew install ripgrep)
/v1/responses reachable
- OPENCLAW_GATEWAY_TOKEN set if your gateway requires authInstall (skill runtime)
This skill installs RAGLite into a skill-local venv:
./scripts/install.sh
It installs from GitHub:
git+https://github.com/VirajSanghvi1/raglite.git@mainUsage
One-command pipeline (recommended)
./scripts/raglite.sh run /path/to/docs \
--out ./raglite_out \
--collection my-docs \
--chroma-url http://127.0.0.1:8100 \
--skip-existing \
--skip-indexed \
--nodes
Query
./scripts/raglite.sh query ./raglite_out \
--collection my-docs \
--top-k 5 \
--keyword-top-k 5 \
"rollback procedure"
Outputs (what gets written)
In --out youβll see:
*.tool-summary.md*.execution-notes.md*.outline.md*/nodes/*.md plus per-doc *.index.md and a root index.md.raglite/ (cache, run stats, errors)Troubleshooting
--chroma-url, and that Chroma is running.rg --version).Pitch (for ClawHub listing)
RAGLite is a local RAG cache for repeated lookups.
When you (or your agent) keep re-searching for the same non-training data β local notes, school work, medical records, internal docs β RAGLite gives you a private, auditable library:
1) Distill to structured Markdown (compression-before-embeddings) 2) Index locally into Chroma 3) Query with hybrid retrieval (vector + keyword)
It doesnβt replace memory/context β itβs the place to store what you need again.
π‘ Examples
One-command pipeline (recommended)
./scripts/raglite.sh run /path/to/docs \
--out ./raglite_out \
--collection my-docs \
--chroma-url http://127.0.0.1:8100 \
--skip-existing \
--skip-indexed \
--nodes
Query
./scripts/raglite.sh query ./raglite_out \
--collection my-docs \
--top-k 5 \
--keyword-top-k 5 \
"rollback procedure"
π Tips & Best Practices
--chroma-url, and that Chroma is running.rg --version).