Show HN: Local Search Agent – offline RAG, no embeddings, free tier

Local Search Agent, a new Python framework, enables AI agents to search, fetch, and reason over local documents using BM25 keyword search via Meilisearch, avoiding cloud uploads, embeddings, and vector databases. The open-source tool offers a free tier with Google AI Studio or fully local setup via Ollama, addressing issues like stale indexes and black-box retrieval in traditional RAG systems.

Give your AI agent a search engine for your local files. Local Search Agent is a Python framework that gives your AI agent a search engine for your local files and lets it search, fetch, and reason over your local documents — the same way a researcher searches the web, but entirely on your machine. Point it at a folder. Ask a question. The agent searches your documents, reads the relevant ones, and gives you an answer with citations — no cloud upload, no API calls to external search services, no embeddings, no vector stores. "What was the AWS spend in Q3?" → agent searches index → fetches relevant docs → answers with sources Traditional RAG Retrieval-Augmented-Generation has a fundamental problem: it converts your documents into embeddings and stores them in a vector database. That means: Stale indexes — embeddings go out of date silently. You never know if the agent is reading your latest documents or a six-month-old snapshot Black-box retrieval — you can't see why a document was retrieved or not. Debugging poor answers is guesswork Chunking anxiety — split too small and you lose context. Split too large and retrieval quality degrades. There's no right answer Infrastructure overhead — a vector database is another service to run, maintain, and pay for Semantic drift — embeddings are sensitive to how questions are phrased. A question about "cloud expenditure" may never match a document that says "AWS spend" Local Search Agent takes a different approach: BM25 keyword search via Meilisearch, structured metadata, and a LangGraph agent loop with tools . The agent searches your document index the same way a developer searches Stack Overflow — with real queries, real results, and full transparency into what was retrieved and why. The result is deterministic, auditable, and fast. You can see exactly what the agent fetched for every answer. 1. INGEST Your documents → parsed, cleaned, chunked, indexed into Meilisearch 2. SERVE FastAPI file server makes documents available to the agent via HTTP 3. SEARCH LangGraph agent loop: search local index → fetch local url → reason 4. ANSWER Agent returns an answer with inline source citations Everything runs locally. Meilisearch downloads automatically on first use, no manual setup. 0.3.0 Release — Watch the Role-based Access Control https://youtu.be/Wjx1Bc0D9uM 0.2.1 Release — Watch the Zooming + Exporting conversation https://youtu.be/TpYN-ytgmXk 0.2.0 Release — Watch the Reranker + Watch mode https://youtu.be/6zqhHxmEkBY Native UI — Watch the UI design and configuration video demo https://youtu.be/J-POiSDbArs CLI AGENT — Watch the Terminal document querying video demo https://youtu.be/ZIiN4NG5g3U Python API — Watch the Local Search Agent API Integration video demo https://youtu.be/JfoLKScLi1Y pip install local-search-agent Google AI Studio free tier — recommended or paid from openai or anthropic local-search config set-key --provider google --key YOUR KEY Or use Ollama for a fully local, zero-cost setup no key needed Install from https://ollama.com Download any model that support function calling and system instructions: ollama pull gemma4:e2b 7.2GB ollama pull gemma4:e4b 9.6GB ollama pull nemotron-3-nano:4b 2.8GB Highly recommended local-search ui The desktop UI open: - Create a workspace, name it, point it at a directory of files. The "Database path" field is optional — leave it blank to use the default location shown in the hint, or paste a custom path and click "Set & Restart". - Ingest parse, clean, chunk . - Get a free google api key from ai-studio. - Set your api key at the top bar's right corner, or add a paid key for anthropic\openai . Note: For paid models or ollama, you will need to set model name via the config button at the top bar's right corner. - click Ingest from the left sidebar. - watch the progress bar at the bottom bar, wait until all files marked as completed. - Start asking questions. Create a workspace and ingest documents local-search workspace create finance "C:\my docs" local-search ingest --workspace finance --dirs "C:\my docs" Start the file server keep this running local-search serve --workspace finance Ask a question local-search query "What was the AWS spend in Q3?" --workspace finance --provider google Use interactive mode local-search query --workspace finance --provider google python from local search agent import SearchAgentFramework, SearchAgentConfig config = SearchAgentConfig document dirs= "C:/my docs" , workspace name="finance", provider="google", db path defaults to your OS user config dir — same location as keys.json override only if you need a custom location: db path="D:/mydata/search.db", framework = SearchAgentFramework config framework.ingest and index framework.start file server response = framework.query "What was the AWS spend in Q3?" print response "answer" Wrap an indexed workspace as a tool and plug it into any external AI agent — LangChain, LangGraph, Google Gemini SDK, or any framework that calls a function. python from local search agent import SearchAgentFramework, SearchAgentConfig, LocalSearchTool config = SearchAgentConfig document dirs= "C:/skills" , workspace name="skills", provider="google", model name="gemini-3.1-flash-lite", cheap model for retrieval Index once framework = SearchAgentFramework config framework.ingest and index framework.start file server Create the tool skill tool = LocalSearchTool config Use inside a LangChain / LangGraph agent from langchain core.tools import tool @tool def search skills query: str - str: """Search the skills knowledge base for coding patterns and techniques.""" return skill tool.run query .answer Pass return raw=True to bypass the internal LLM summarisation and return the full document text verbatim — useful when the calling agent should reason over the raw content itself: skill tool = LocalSearchTool config, return raw=True See the Python API Reference https://github.com/wiss84/local-search-agent/blob/main/local search agent/docs/api-reference.md localsearchtool for the full LocalSearchTool documentation. Running this for more than just yourself? Turn one shared deployment into a proper multi-user server with role-based access control — three roles superadmin / admin / member , admin / member granted per subject per workspace, superadmin unconditional across the whole deployment, enforced on every protected route. Also includes optional per-role model/provider cost controls and concurrency/rate-limit management for cloud LLM accounts or shared Ollama hardware. Three pluggable identity providers cover the common setups out of the box: a header provider for when you already have an authenticating reverse proxy in front, an API-key provider with browser sessions for when you don't have existing auth infrastructure, and a JWT provider that validates against your company's own IdP Auth0, Okta, Azure AD, Google Workspace when employees already sign in via SSO. Bootstrap: create a workspace, a superadmin key, an admin's key, and grant admin access local-search workspace create finance "/srv/docs/finance" local-search auth create-key --subject root@acme.com --display-name "IT/Ops" --superadmin local-search auth create-key --subject alice@acme.com --display-name "Alice" --created-by root@acme.com local-search grant-access --subject alice@acme.com --workspace finance --role admin Run the dashboard with RBAC turned on local-search ui --multi-tenant --db /var/lib/local-search-agent/prod.db This is entirely opt-in — set identity provider on SearchAgentConfig or pass --multi-tenant to local-search ui to turn it on; every existing single-user workflow above works exactly as written if you never do. See Role-Based Access Control https://github.com/wiss84/local-search-agent/blob/main/local search agent/docs/role based access control.md for the full guide, and Production Deployment https://github.com/wiss84/local-search-agent/blob/main/local search agent/docs/production-deployment.md for running this as a shared server Docker, systemd, reverse proxy — note that Dockerfile/systemd/Caddy files live at the repo root, not in the PyPI package itself, so self-hosters should either clone this repo or copy the file contents straight out of that doc. By default, scanned or image-based PDFs are processed using RapidOCR. Installing Tesseract enables a faster OCR path ~5 second per page vs. minutes without it . Digitally-created PDFs with a text layer are never affected — they use direct text extraction and skip OCR entirely. Windows Download and run the installer from https://github.com/UB-Mannheim/tesseract/wiki https://github.com/UB-Mannheim/tesseract/wiki Make sure "Add Tesseract to the system PATH" is checked during installation. Linux sudo apt install tesseract-ocr Ubuntu / Debian sudo dnf install tesseract Fedora / RHEL sudo pacman -S tesseract Arch macOS brew install tesseract After installation, restart the application — Tesseract is detected automatically. If it's not found, ingestion continues normally using RapidOCR with no errors. | Format | Extension | |---|---| .pdf | | | Word | .docx | | Excel | .xlsx | | PowerPoint | .pptx | | HTML | .html , .htm | | Plain text | .txt , .md | | CSV | .csv | | JSON | .json | | XML | .xml | .eml | One command install — pip install local-search-agent . Meilisearch downloads automatically No embeddings, no vector stores — BM25 search with structured metadata. Fast, deterministic, auditable Native desktop UI — pywebview window with live streaming agent responses, workspace management, and chat history Multi-provider LLM — Google, Ollama local , OpenAI, Anthropic Multi-workspace — isolate document collections by department, project, channel, or topic. Each workspace is its own search index Incremental sync — background scheduler re-indexes only changed files. A 10,000-document corpus with 50 changes re-indexes only the 50 Multi-tenant RBAC — opt-in three-role access control superadmin / admin / member per workspace, with pluggable identity header, API key, or JWT/SSO , plus optional per-role model/provider cost controls and concurrency/rate-limit management, for running one shared deployment across a team Full CLI parity — everything you can do in the UI you can do from the terminal Python API — embed the framework directly in your own application Cross-platform — Windows, macOS, Linux | Guide | Description | |---|---| | Installation https://github.com/wiss84/local-search-agent/blob/main/local search agent/docs/installation.md Architecture https://github.com/wiss84/local-search-agent/blob/main/local search agent/docs/architecture.md CLI Reference https://github.com/wiss84/local-search-agent/blob/main/local search agent/docs/cli-reference.md Python API Reference https://github.com/wiss84/local-search-agent/blob/main/local search agent/docs/api-reference.md Configuration https://github.com/wiss84/local-search-agent/blob/main/local search agent/docs/configuration.md Ingestion https://github.com/wiss84/local-search-agent/blob/main/local search agent/docs/ingestion.md Multi-Workspace https://github.com/wiss84/local-search-agent/blob/main/local search agent/docs/multi-workspace.md Role-Based Access Control https://github.com/wiss84/local-search-agent/blob/main/local search agent/docs/role based access control.md Production Deployment https://github.com/wiss84/local-search-agent/blob/main/local search agent/docs/production-deployment.md Semantic Search https://github.com/wiss84/local-search-agent/blob/main/local search agent/docs/semantic-search.md Troubleshooting https://github.com/wiss84/local-search-agent/blob/main/local search agent/docs/troubleshooting.md Contributions are welcome. Clone the repo and install in editable mode with dev dependencies: git clone https://github.com/wiss84/local-search-agent.git cd local-search-agent pip install -e ". dev " Run tests before submitting a PR: pytest tests/ -v --cov=local search agent --cov-report=term-missing ruff check . ruff format . MIT — see LICENSE https://github.com/wiss84/local-search-agent/blob/main/LICENSE for details. Built by Wissam Metawee https://github.com/wiss84