# Storia-AI/sage

Chat with any codebase in under two minutes | Fully local or via third-party APIs

Repository: https://github.com/Storia-AI/sage
Canonical: https://ross.abutalabs.com/products/storia-ai-sage
Homepage: https://sage.storia.ai
Language: Python
License: Apache-2.0
License Family: permissive
Topics: ai, anthropic, claude, copilot, developer-tools, langchain, llm, openai, pinecone, python, rag, hacktoberfest, hacktoberfest-2024, hacktoberfest2024
Archived: true
Last push: 2024-11-11T04:49:34+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 52
- inputs: {"age_days": 740, "days_push": 660, "days_rel": 660, "gap_med": null, "n_releases_24m": 1}
- flags: archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1268, forks 116 (observed 2026-08-28T04:04:11.527814+00:00)

## What it is
Sage is an open-source tool that lets developers chat with any codebase to quickly understand how it works, similar to a self-hosted GitHub Copilot for code comprehension. It supports fully local pipelines via Ollama and Marqo or third-party LLM APIs like OpenAI and Anthropic, with configurable retrieval strategies including lightweight LLM-based retrieval and traditional RAG indexing.

## Use cases
- chat with a codebase to understand how it works
- onboard onto an unfamiliar open-source repository quickly
- ask questions about how to integrate a library into my project
- run a private local code Q&A assistant without sending code to the cloud
- index a repository and query it with RAG
- compare embedding and retrieval strategies for code search

## When to choose
- you need to understand a large or unfamiliar codebase fast
- privacy matters and you want a fully local LLM pipeline with Ollama
- you want tunable retrieval strategies and documented benchmarks
- you prefer an open-source alternative to hosted code assistants

## When to avoid
- you need inline code completion or IDE autocomplete rather than codebase Q&A
- you want a zero-setup hosted product without running your own infrastructure
- your project requires long-term enterprise support or a mature release cadence

## Facets
- artifact type: application
- maturity: active
- function: rag, llm-inference, search-engine, chatbot, agent-framework
- domain: developer-tools, large-language-models, artificial-intelligence
- platform: python, self-hosted, cross-platform
- tags: codebase-chat, github-copilot-alternative, ollama, vector-store, code-understanding, langchain, openai, anthropic, retrieval-augmented-generation, docker

## Member repositories
- Storia-AI/sage (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:11.527814+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T05:03:35.940975+00:00, confidence not recorded.
  - readme: https://github.com/Storia-AI/sage (fetched 2026-08-28T04:04:11.527814+00:00, sha fbd8ba235975)
- Data as of 2026-08-30T08:39:29.467469+00:00.