MLX LM vs PrivateGPT

MLX LM 37

Read for the HTTP server, the surface an agent calls. No OpenAPI file or other machine-readable contract. SERVER.md says the API is intended to be similar to OpenAI's chat API (5 of 25). No llms.txt. The docs are Markdown files in the repository, 176 lines for the server (5 of 10). Request and response fields each have a one-line purpose, the page opens with the production warning, and stop gained a fuller description in October, but tools, seed, max_completion_tokens, chat_template_kwargs, image content parts, the /v1/completions route and /health are in the code and not in the docs (9 of 20). Types and defaults are given in prose, and the server checks types and ranges in code. We found no response_format or JSON schema output in server.py (6 of 15). Two curl examples and no documented error responses (5 of 15). Version tags (v0.32.0 to v0.32.2 since 30 September) and GitHub release notes, with no changelog file and no version on the API itself beyond the /v1 path (7 of 15). 5 + 5 + 9 + 6 + 5 + 7 = 37.

PrivateGPT 83

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, with the messages API modelled on Anthropic's (25). docs.privategpt.dev serves llms.txt, a Markdown copy of every page and a docs MCP server (10). The docs explain each endpoint group, startup and model discovery, and a compatibility table says which parts of the Claude API are supported, partial or missing, such as prompt caching and OAuth (15 of 20). Pydantic models with literal type discriminators and required fields, while settings and tool context are wide objects (12 of 15). curl examples for each guide and a /v1/messages/validate route, with error shapes not documented as a list (9 of 15). /v1 paths and a dated changelog, though releases trail main by more than four months (12 of 15). 25 + 10 + 15 + 12 + 9 + 12 = 83.

MLX LM 81

Tag v0.32.2 on 16 October 2026, 19 days before this check (30). Three tagged releases in the 90 days from 6 August, v0.32.0 (30 September), v0.32.1 (15 October) and v0.32.2 (16 October), each with code changes, and each tag push publishes to PyPI through the release workflow. PyPI itself could not be read on 4 November (20). 146 commits from 87 authors on main since 6 August, the newest on 30 October. Recent bug reports mostly had no reply or one comment on 8 October, not re-read, and reply times were not measured (15 of 25). The package is the Python library, current with the release. No other official client (8 of 15). CI on every push, a pre-commit lint job, PyPI publishing by trusted publishing, and dependency floors on recent versions (mlx>=0.32.3, transformers>=5.7.0). No Dependabot file (8 of 10). 30 + 20 + 15 + 8 + 8 = 81.

PrivateGPT 41

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). No release or dated changelog entry in the 90 days since 8 August (0 of 20). Maintainers commit most days and outside pull requests merged in October, but 23 pull requests are open and the stale bot closes issues, including two security reports, with no maintainer reply (13 of 25). Homebrew tap, wheel index and Docker images ship with releases, and Anthropic SDKs work against it. No product MCP server of its own, though it connects to remote MCP servers (10 of 15). Dependabot, uv.lock, actions pinned by commit since 19 October and dependency CVE upgrades in June, July and August (8 of 10). 10 + 0 + 13 + 10 + 8 = 41.

MLX LM 56

Read with the local-software lines, since the package and its server run on the owner's machine. pyproject.toml states Python 3.11 or later with macOS and Linux classifiers, each version tag is published to PyPI by trusted publishing from release.yml, and conda-forge carries it per the 8 October check (20). The Build and Test workflow runs a lint check and the unit tests (21 test files) on every pull request and push to main, on self-hosted macOS runners since 30 October. Run results on GitHub could not be read on 4 November, so the line takes 15, the value for public CI that runs the tests with an unreadable result (15 of 25). 151 open issues and 74 open pull requests, with no reply or one comment on the newest bug reports, among them server bugs #1946 and #1909, per the 8 October check, not re-read (15 of 25). Version tags with GitHub release notes and no changelog file. The notes could not be read on 4 November, and none of the ten read on 8 October called out a breaking change (6 of 15). Version 0.32.2, pre-1.0, and the server docs still say it is not recommended for production (0). 20 + 15 + 15 + 6 + 0 = 56.

PrivateGPT 70

Read with the local-software lines, since PrivateGPT runs on the owner's hardware with no hosted service behind it. Homebrew tap, uv tool install from Zylon's own wheel index (not PyPI) and Docker Hub images zylonai/private-gpt 1.0.1 of 18 June 2026. Python 3.11 only, stated in pyproject.toml, and it needs a separate OpenAI-compatible model server (17 of 20). tests.yml runs format, lint, typecheck and the tests affected by each push on main, with the full suite of 217 test files on release pull requests. We couldn't see run results because the GitHub API refused us, and issue #2441 of 1 November reports the Claude spec update workflow failing (15 of 25). GitHub shows 3 open issues of about 1,250, because a stale bot closes quiet issues, two security reports among them, with no maintainer reply (12 of 25). release-please keeps a changelog with breaking changes marked, but no release has been cut since 1.0.1 while main carries 51 commits since 8 August, among them a breaking observability change of 23 October (11 of 15). Version 1.0.1 (15). 17 + 15 + 12 + 11 + 15 = 70.

MLX LM 54

Read for an API. max_tokens defaults to 512, stop and logprobs shape the output and usage reports token counts, but there is no field selection and no structured output mode (15 of 25). GET /v1/models lists the MLX models in the Hugging Face cache and can be narrowed to one repository by path. No paging and no token-counting route (10 of 20). Errors are {"error": "<text>"} with 400 and a specific message for a bad field, 411 for a missing Content-Length, and 404 for any failure while loading a model or building the prompt. There are no codes and none of it is documented (8 of 20). Generation is stateless and safe to retry, seed is accepted, a prompt cache holds ten entries by default and /health answers 503 when the generation thread has stopped. No retry guidance (12 of 20). Only messages is required and the defaults are conservative. OpenAI clients can call the chat route, and the Python API (load, generate, stream_generate) ships in the same package. No client library in a second language in this repository (9 of 15).

PrivateGPT 64

Read for an HTTP API an agent calls on a local instance. Token counting, top_k style retrieval settings, citation output and response byte caps let a caller size context (18 of 25). Artifact listing by namespace and retrieval filters, with no documented cursor pagination (12 of 20). FastAPI validation errors name the field and the validate route checks a request before running it, but there is no error catalogue (12 of 20). Async messages and ingestion return task ids with status, cancel and delete routes. No idempotency keys were found (10 of 20). Anthropic SDKs and Claude Code work by pointing ANTHROPIC_BASE_URL at the server, but a model server and an embedding server have to be configured first (12 of 15). 18 + 12 + 12 + 10 + 12 = 64.

MLX LM 69

The editorial half. MIT, copyright Apple Inc., all of it public (30). No privacy statement covers the software and nothing states what it sends. In the source the outbound calls are model downloads from Hugging Face (or ModelScope when MLXLM_USE_MODELSCOPE is set), image URLs named in a chat request (since v0.32.1), uploads only on command, and a calibration text fetched from a GitHub gist by the quantisation tools (12 of 30). Runtime messages say python -m mlx_lm.<command> is deprecated, with no date and no written policy (5 of 20). No telemetry, analytics or update check found in the source at the 30 October head, so nothing to opt out of, though the README does not say so (18 of 20). 30 + 12 + 5 + 18 = 65.

PrivateGPT 64

Apache-2.0 (30). The OpenAPI description says no data leaves the execution environment, but the docs list cloud gateways as model providers and web search goes to outside services when enabled, and no privacy statement covers the software. Zylon's privacy policy covers its website (15 of 30). The 1.0 rewrite was marked as a breaking change in the changelog, and there is no deprecation policy (6 of 20). No telemetry to Zylon found in the source. OpenTelemetry tracing is off by default and its exporters write local files or to the owner's collector, documented on the observability page (16 of 20). 30 + 15 + 6 + 16 = 67.