Lemonade vs PrivateGPT

Lemonade 76

Stable release v2026.44.1 tagged on 28 October 2026 (30). Twelve stable releases in the 90 days from 4 August, from v11.5.2 (5 August) through v11.9.0 (1 September), v2026.39.1 (23 September), v2026.40.0, v2026.41.1, v2026.42.1 (14 October) and v2026.43.3 (21 October) to v2026.44.1, with a candidate every week, by the repository's tags (20). New issues were labelled by area and engine within a day or two on 8 October, and a Discord server is linked from the README. Comment threads weren't read, and GitHub's pages answer 403 in our session (15 of 25). The official MCP registry returned no entry for Lemonade on 2 November and there's no Lemonade client SDK, though OpenAI, Anthropic and Ollama SDKs work against it (5 of 15). A large CI matrix with self-hosted GPU and NPU runners, but the main workflow's badge read failing on 8 October and Dependabot is set up for dev containers only (6 of 10). 30 + 20 + 15 + 5 + 6 = 76.

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.

Lemonade 70

We found no OpenAPI or Swagger file in the repository. The six MCP tools carry JSON Schema inputs from tools/list, though messages and tools are arrays of untyped objects and stop and tool_choice have empty schemas (12 of 25). No llms.txt at lemonade-server.ai (404). Every running server returns its own Markdown API reference at GET /v1/docs and through the lemonade_docs tool, so the reference matches the installed version and works offline (8 of 10). MCP tool descriptions say what to call first, which argument to prefer and what a wrong model name costs, and the API reference marks each OpenAI parameter as available or not (17 of 20). One enum (response_format on transcription), a minimum on n and required fields are declared, and the rest is typed loosely (8 of 15). Request examples in PowerShell and bash throughout, error tables on some endpoints and a JSON-RPC error table for MCP, but no single error reference (12 of 15). Notes with Headline and Breaking Changes sections on every release, kept in the lemonade-testing repository, and versioned route prefixes, with no CHANGELOG file (13 of 15). Re-read on 2 November at commit 17193fd, the six MCP tools and the missing OpenAPI file are unchanged. 12 + 8 + 17 + 8 + 12 + 13 = 70.

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.

Lemonade 70

Read with the MCP lines for /mcp and the API lines for the OpenAI-compatible routes. Six tools, with long descriptions (22 of 25). max_tokens caps output, output_dir returns file paths in place of inline base64, and lemonade_list_models has two include flags. We found no pagination on list routes (12 of 20). OpenAI-style error objects with a type and message, tool failures returned as isError: true with text a model can act on, and 501 on unsupported Ollama routes. No Retry-After or overload guidance found (15 of 20). No readOnlyHint or destructiveHint in the tool definitions and no idempotency keys. allow_download defaults to false, so a call can't start a download unless asked, and inference calls are safe to repeat (9 of 20). model is optional on the MCP tools, lemonade launch claude configures Claude Code in one command, and existing OpenAI, Anthropic and Ollama clients work unchanged, with no Lemonade client SDK (12 of 15). Re-read on 2 November, the tool definitions still carry no annotations, though the tool loader now accepts an annotations object. 22 + 12 + 15 + 9 + 12 = 70.

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.

Lemonade 75

Read with the local-software lines, since Lemonade runs on the owner's hardware with no hosted service behind it, though the listing's kind is http-api. Official installers for each platform (Windows MSI and winget, macOS pkg, Ubuntu PPA and Snap, Debian deb, Fedora rpm, an Arch package and a container on ghcr.io), with supported systems and a backend-by-device table in the README (20). A public CI builds and tests every platform with C++ unit tests, Python server tests and, since 15 October, model-backed conformance tests, and an MCP smoke test runs beside it. On 8 October 2026 the main build, test and release workflow's badge read failing on main, per the 8 October check, not re-read on 2 November because GitHub's pages answer 403 in our session (15 of 25). 411 issues and 158 pull requests were open on 8 October, with new reports labelled within a day or two; not re-read on 2 November (15 of 25). Versions are year.week.number, so the number carries no compatibility signal, but every release's notes have a Breaking Changes section, empty when there are none (v2026.44), and candidates carrying each change are published a week before stable (10 of 15). A stable channel separate from weekly candidates, and v11.9.0 before the scheme changed (15). 20 + 15 + 15 + 10 + 15 = 75.

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.