Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Pharos — local-first agentic RAG for your team's document library: multi-format ingest, hybrid retrieval, enterprise ACL, dual HTTP + MCP exits.
| Date | Stars |
|---|---|
| 2026-07-31 | 291 |
| 2026-08-06 | 291 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<div align="right"> **English** | [中文](README.zh.md) </div> <div align="center"> <img src="docs/assets/pharos-banner.svg" alt="Pharos — navigation for your team's document library" width="880"> # Pharos [](https://github.com/Laurent00TT/pharos/actions/workflows/ci.yml) [](LICENSE)   [](docs/learning/) **Turn PDFs, scans, docx, pptx and xlsx into a local knowledge base you can ask questions of — with enterprise access control and citations you can trace back to the page.** Each RAG component was sharpened on its own, then folded into one repository: multi-identity auth, observability and systemd supervision come with it. </div> > **A note on language.** The code, CLI and commit history are in English; the > documentation — including the 12-part learning series — is written in Chinese. > This README is the English entry point and covers what the system is, how it is > put together and how to run it. For anything deeper, you will be reading Chinese > (or machine-translating it). --- > The Lighthouse of Alexandria stood beside the Library, guiding ships to shore. **Pharos does the same job, except what it lights up is your team's document library.** This is not another chunking toy. Every significant decision here is backed by a measurement, argued through several rounds of adversarial review, and is running today over 77 real documents and 7,652 chunks. Installing it is one line: `pip install -e '.[dev]'` (src-layout, editable). ## Two exits, one set of semantics One knowledge base, one door for each kind of consumer: | Exit | Command | Who uses it | What it does | |---|---|---|---| | **HTTP API** | `pharos serve` | curl, scripts, frontends | Closed-pipeline QA: `/v1/ask` runs retrieve → grounding → DeepSeek → an answer with citations, plus six retrieval endpoints | | **MCP** | `pharos mcp` | agents such as Claude Code | Agentic RAG: when to retrieve, how to rewrite, whether to go multi-hop — the agent decides | Both doors share one set of semantics, held in place by two rules: the tool contract has exactly one source (`toolcore`, so the stdio and HTTP sides cannot drift), and identity is decided server-side (an agent cannot edit its own permissions). ## Architecture <div align="center"> <img src="docs/assets/architecture.svg" alt="Pharos architecture: consumers → daemon → backing services" width="100%"> </div> **Why a resident daemon?** Embedded Qdrant admits a single client and holds an exclusive lock, and an 8B model takes a minute or two just to load. Under the earlier stdio-direct design, every agent session spawned its own process — fighting over the lock and reloading the model each time. Pharos inverts that: the daemon owns the heavy resources, MCP shrinks to a thin HTTP adapter that starts in milliseconds, and every session shares one already-warm backend. The trade-offs behind this are in [docs/DESIGN.md](docs/DESIGN.md) (Chinese). <details> <summary><b>Production shape: from one box to three independently scalable tiers</b></summary> <br/> The single-node problem is that the GPU model, embedded Qdrant and application logic all live in one process, so horizontal scaling hits a ceiling immediately. Split apart, there are three tiers that scale independently: - **`inference`** (FastAPI on `:8900`) — GPU forward passes lifted out on their own, returning full-width vectors that the client then truncates, with both sides kept equivalent; - **`pharos`** — the applicati
Excerpt of 12,360 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:46d4fdc2960b043a, topic:rag, topic:retrieval-augmented-generation
matched fp:46d4fdc2960b043a, topic:llm
matched fp:46d4fdc2960b043a, topic:embeddings
matched fp:46d4fdc2960b043a, topic:mcp, topic:model-context-protocol