← Back to Skills Marketplace
LiteRAG
by
Mozi Arasaka
· GitHub ↗
· v0.2.2
· MIT-0
95
Downloads
0
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install literag
Description
Local retrieval skill for large documentation corpora using independent SQLite knowledge libraries with keyword plus vector hybrid search. Use when searching...
README (SKILL.md)
LiteRAG
Use this skill when the target corpus is too large or too noisy for main agent memory.
Install
Packaged dependency install:
python3 -m pip install -r {baseDir}/requirements.txt
Layout
- Config + databases live under
\x3Cworkspace>/.literag/ - Main config:
\x3Cworkspace>/.literag/knowledge-libs.json - Default workspace resolution order:
OPENCLAW_WORKSPACE→WORKSPACE→ walk upward from the current path until the OpenClaw workspace sentinel files are found - Core scripts live under
skills/literag/scripts/ - Skill bin entrypoint:
skills/literag/bin/literag - Workspace convenience wrappers live at
scripts/literag-query.py,scripts/literag-index.py,scripts/literag-status.py,scripts/literag-meta.py, andscripts/lq
Rules
- Keep personal/work memory in OpenClaw builtin memory
- Keep large external corpora in LiteRAG, not
memory_search - Treat each knowledge base as an independent library with its own SQLite
- Search first, inspect second
- Prefer grouped document hits over raw chunk spam
- Prefer source-relative paths when citing files back to the user
- Use local OpenAI-compatible embeddings by default unless explicitly changed in config
Read these files when needed
- Always read
\x3Cworkspace>/.literag/knowledge-libs.jsonwhen targeting a library or changing config - Read
references/usage.mdwhen you need command examples, output schema, or the intended search → inspect workflow - Read
references/configuration.mdwhen adding libraries, source roots, excludes, chunking overrides, or ranking overrides - Read
references/agent-prompts.mdwhen another agent / ACP harness needs a ready-made LiteRAG prompt template - Read
references/optimization-playbook.mdwhen a specific library needs retrieval-quality tuning, ranking cleanup, or indexing-throughput tuning - Read scripts under
skills/literag/scripts/only when editing behavior or diagnosing bugs
Slash / user-invocable usage
When invoked as /literag ..., parse the remaining argument string as a subcommand.
Supported forms:
/literag search \x3Clibrary> \x3Cquery>/literag inspect \x3Clibrary> \x3Cpath> [--start N --end N]/literag index \x3Clibrary> [--limit-files N] [--embedding-batch-size N]/literag index-all [--limit-files N] [--embedding-batch-size N]/literag status \x3Clibrary>/literag meta \x3Clibrary>/literag benchmark \x3Clibrary> --query ...
If the user gives a natural-language request instead of a strict subcommand, translate it to the nearest supported operation instead of being pedantic.
Supported commands
index_library.py— index one libraryindex_all.py— index all configured librariessearch_library.py— grouped hybrid/fts/vector retrievalinspect_result.py— expand a hit by file path + chunk rangestatus_library.py— show index health / compatibility / countsmeta_library.py— dump raw sqlitemetarecordsbenchmark_library.py— benchmark hybrid/fts/vector latency + hit shape across fixed query setsbin/literag— packaged CLI entrypoint for search / inspect / index / status / meta / benchmarkscripts/literag-query.py— query/search/inspect wrapperscripts/literag-index.py— index wrapper for one library or all librariesscripts/literag-status.py— status wrapperscripts/literag-meta.py— meta wrapperscripts/literag-benchmark.py— benchmark wrapperscripts/lq— tiny shell alias forliterag-query.py
Operating workflow
- Read
\x3Cworkspace>/.literag/knowledge-libs.json - Resolve the target library
- Run
search_library.pyfor grouped retrieval - If needed, run
inspect_result.pyon the top hit or chosen range - For quick operator use, prefer
scripts/literag-query.pyorscripts/lq - Use
scripts/literag-index.pywhen you need a short indexing entrypoint - Use
scripts/literag-status.pybefore debugging weird retrieval or after config changes - Use
scripts/literag-meta.pywhen you need the raw stored metadata - Use
scripts/literag-benchmark.pyorskills/literag/scripts/benchmark_library.pywhen you need repeatable retrieval latency / hit-shape comparisons - Keep LiteRAG separate from builtin memory unless the user explicitly wants a durable summary copied into workspace memory
Current intent
Use LiteRAG for:
- Blender manual + Blender Python reference
- Future blog/article/site knowledge bases
- Any large external docs where hybrid retrieval is needed without polluting builtin memory
Usage Guidance
This skill appears to be what it says: a local SQLite-based hybrid search/indexer. Before installing/use: 1) Inspect <workspace>/.literag/knowledge-libs.json — it may contain an embedding.baseUrl and apiKey; ensure the endpoint is trusted (default is localhost) because document text will be sent there for embeddings. 2) Review the configured library 'paths' to confirm only the intended files will be indexed (the tool will read and store chunks from those paths). 3) Install requirements (sqlite-vec) in a controlled environment — it may require native extensions or a Python build with SQLite extension-loading support. 4) Be aware that the sqlite DBs and metadata live under <workspace>/.literag/ and should be protected if they contain sensitive content. If you want to avoid any network leakage, set embedding.baseUrl to a trusted local endpoint or disable vector embeddings in config.
Capability Analysis
Type: OpenClaw Skill
Name: literag
Version: 0.2.2
The LiteRAG skill bundle is a legitimate implementation of a local Retrieval-Augmented Generation (RAG) system using SQLite with FTS5 and vector search capabilities. The code in 'literag_common.py' and associated scripts handles document indexing, chunking, and hybrid retrieval through standard OpenAI-compatible embedding endpoints (defaulting to localhost). No evidence of data exfiltration, malicious execution, or harmful prompt injection was found; the instructions in 'SKILL.md' and 'agent-prompts.md' are appropriately focused on guiding the agent to use the retrieval tools effectively for documentation queries.
Capability Tags
Capability Assessment
Purpose & Capability
Name/description (local hybrid SQLite retrieval and indexing) match the included scripts and declared runtime needs. The only required binary is python3 and the code implements indexing, search, inspect, status, meta, and benchmark workflows that align with the stated purpose.
Instruction Scope
SKILL.md and the scripts consistently instruct the agent to read workspace config (.literag/knowledge-libs.json), iterate configured source paths, and run local indexing/search scripts. This is expected for a local retrieval tool. Note: the indexer will read files under the configured library paths and will send texts to the configured embedding endpoint (embedding.baseUrl) during indexing/search, which is necessary for embedding-based retrieval.
Install Mechanism
There is no automatic install spec; SKILL.md recommends running pip install -r requirements.txt. requirements.txt contains sqlite-vec (a native-backed package). No remote arbitrary downloads or URL/extract installs are present in the bundle. Installing sqlite-vec may require native build support or a Python+SQLite build that allows loading SQLite extensions—this is an expected but higher-footprint dependency for vector search.
Credentials
The skill declares no required env vars and reads only OPENCLAW_WORKSPACE / WORKSPACE / LITERAG_PYTHON for workspace resolution and preferred python. However, sensitive credentials (embedding.apiKey) are stored in the librag config (.literag/knowledge-libs.json) rather than environment variables; the skill will use that apiKey and the embedding.baseUrl to contact an embedding provider. This is proportionate for an indexer, but you should verify the config and endpoint are trusted before indexing.
Persistence & Privilege
The skill is not always-enabled (always: false) and is user-invocable only. It does not request persistent platform privileges. It stores DBs/config under the workspace (.literag/) which is expected for a local indexer.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install literag - After installation, invoke the skill by name or use
/literag - Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.2.2
Clarify workspace-relative .literag paths and document environment overrides used for workspace and Python resolution.
v0.2.1
Initial public release with sqlite-vec backend, packaged CLI, metadata, and docs.
Metadata
Frequently Asked Questions
What is LiteRAG?
Local retrieval skill for large documentation corpora using independent SQLite knowledge libraries with keyword plus vector hybrid search. Use when searching... It is an AI Agent Skill for Claude Code / OpenClaw, with 95 downloads so far.
How do I install LiteRAG?
Run "/install literag" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is LiteRAG free?
Yes, LiteRAG is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does LiteRAG support?
LiteRAG is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created LiteRAG?
It is built and maintained by Mozi Arasaka (@mozi1924); the current version is v0.2.2.
More Skills