# PrivateGPT (slim) > PrivateGPT is Zylon's open-source server that puts an Anthropic-style messages API, document ingestion, retrieval with citations, built-in tools and MCP connectors in front of any OpenAI-compatible local model server. The owner runs it. - Full: https://www.anchorterminal.com/tools/privategpt.md (~7,400 tokens) · this version ~1,580 tokens · JSON https://www.anchorterminal.com/tools/privategpt.json · canonical https://www.anchorterminal.com/tools/privategpt - Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-07 · pricing https://www.anchorterminal.com/tools/privategpt#pricing · reviews https://www.anchorterminal.com/tools/privategpt#reviews - Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data) **D · 53.2/100 · rank #954 of 1486 · #11 in Local AI · not agent-ready · confidence medium** Assessment: PrivateGPT 1.0 is an Apache-2.0 server that gives local models an Anthropic-style messages API with retrieval, citations, tools and MCP, documented by an OpenAPI file and llms.txt. A default start has authentication off, listens on every interface and reads local paths given as URIs, and a public report of that was closed without a reply. ## Facts - Kind: HTTP API · vendor: Zylon (PriBAI Technology Spain S.L.) · category: Local AI · legal entity: PriBAI Technology Spain S.L. · provenance 61/100 - Local only (HTTP): oci `zylonai/private-gpt` - Auth: None · pricing: Free · x402: no · licence: Apache-2.0 - Benchmark probes: not run yet, so Performance is pending - Surface listed: The PrivateGPT 1.0 server and its REST API on the owner's machine, read from a clone of github.com/zylon-ai/private-gpt (newest commit 29 October 2026), docs.privategpt.dev and zylon.ai on 6 November 2026. Nothing was installed or run - Which PrivateGPT: The zylon-ai/private-gpt project, first released in May 2023 per CITATION.cff. Zylon's enterprise platform on top of it is a separate, sales-led product - Model servers: Ollama, LM Studio, llama.cpp's server, vLLM or any OpenAI-compatible endpoint, including cloud gateways listed in the docs. Embeddings come from a second endpoint - API: `POST /v1/messages` with streaming, async jobs and token counting, `/v1/models`, `/v1/artifacts/*` ingestion, `/v1/files`, `/v1/embeddings`, `/v1/skills`, and tool routes for semantic search, web search, web fetch, database queries and tabular analysis - Not supported: Prompt caching and OAuth or organisations, per the README's Claude API compatibility table. Skills are basic - Install: Homebrew tap, `uv tool install` from wheels.privategpt.dev with Python 3.11, or Docker images `zylonai/private-gpt` - Observability: OpenTelemetry traces of requests, model calls, tools, sandbox steps and ingestion, off by default (`PGPT_OBSERVABILITY=none`), written to local JSON lines or the owner's OTLP collector - Legal entity: PriBAI Technology Spain S.L., trading as Zylon, Calle Antoñete 7, Valdemorillo, 28210 Madrid, per the zylon.ai terms - Scores: Reliability 70, Performance pending, Schema & documentation 83, Agent ergonomics 64, Security & auth 32, Payments & pricing 60, Task success pending, Maintenance & community 41, Transparency & trust 64 · negative events -7 · total over the 7 assessed categories - Why: Reliability, Read with the local-software lines, since PrivateGPT runs on the owner's hardware with no hosted service behind it. · Schema & documentation, An OpenAPI file of 38 paths in the repository (fern/openapi/openapi.json, version 1.0.1), also served by each instance at /openapi.json, wit… · Agent ergonomics, Read for an HTTP API an agent calls on a local instance. · Security & auth, Read with the tool checklist. · Payments & pricing, Read with the self-hosted rule. · Maintenance & community, The last release is 1.0.1, dated 16 June 2026 in the changelog and tagged 18 June, 141 days before the check (10 of 30). · Transparency & trust, Apache-2.0 (30). - Sources: 12, open questions: 6, both in the full twin - Capabilities: inference.local, memory.search, agent.mcp-client - JSON: https://www.anchorterminal.com/api/v1/tools/privategpt.json - Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/privategpt.svg` or a link to https://www.anchorterminal.com/tools/privategpt from a page on privategpt.dev or one of its subdomains, or the README at the root of github.com/zylon-ai/private-gpt, then `POST https://www.anchorterminal.com/api/v1/verify` `{"slug", "url"}` or `verify_listing` at /mcp; re-checked weekly, no effect on the grade. Snippets in the full twin. - Support: Discord https://discord.gg/F8KCFeZbkx; hello@zylon.ai; https://docs.privategpt.dev/introduction; https://github.com/zylon-ai/private-gpt/blob/main/SECURITY.md; more in the full twin ## Before you call it 1. Turn on `server.auth` and bind to 127.0.0.1 before exposing an instance, since a default start answers any caller 2. Point Anthropic SDKs or Claude Code at the server with `ANTHROPIC_BASE_URL=http://localhost:8080` 3. Start an OpenAI-compatible model server and an embedding server first, and set `OPENAI_API_BASE` and `OPENAI_EMBEDDING_API_BASE` 4. Pass ingested documents through `tool_context` to get answers with citations 5. Treat web fetch, search and MCP results as untrusted, since PrivateGPT documents no prompt-injection handling ## Connect ```bash brew tap zylon-ai/tap brew install private-gpt ``` ```bash curl http://localhost:8080/v1/messages \ -H "Content-Type: application/json" \ -d '{"model": "qwen3.5:35b", "messages": [{"role": "user", "content": "Explain retrieval-augmented generation."}]}' ``` Full config and headless snippets are in the full page. Through letme (picks today, calling later): https://letme.dev/privategpt ## Similar tools | Tool | Grade | Score | Shared capabilities | Slim | | --- | --- | --- | --- | --- | | screenpipe | C | 61 | memory.search, agent.mcp-client, inference.local | https://www.anchorterminal.com/tools/screenpipe.min.md | | AnythingLLM | E | 42.1 | inference.local, memory.search, agent.mcp-client | https://www.anchorterminal.com/tools/anythingllm.min.md | | Khoj | E | 38.8 | memory.search, inference.local, agent.mcp-client | https://www.anchorterminal.com/tools/khoj.min.md | | LocalAI | B | 62.5 | inference.local, agent.mcp-client | https://www.anchorterminal.com/tools/localai.min.md | | KoboldCpp | B | 62.1 | inference.local, agent.mcp-client | https://www.anchorterminal.com/tools/koboldcpp.min.md | ## Panel reviews (0, desk reviews from public material, no calls made)