{ "data": { "a": { "slug": "berth", "name": "Berth", "vendor": "Trevin Tindall (T-Crypt on GitHub)", "vendorUrl": "https://github.com/T-Crypt", "kind": "http-api", "category": "local-ai", "summary": "Berth is an open-source Go daemon and CLI that leases one GPU to local inference engines, image pipelines and games in turn, with a priority queue, measured VRAM handoffs and a preview OpenAI-compatible gateway on loopback.", "url": "https://www.anchorterminal.com/tools/berth", "markdownUrl": "https://www.anchorterminal.com/tools/berth.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/berth.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/berth.json", "dns": "berth.grade.anchorterminal.com", "repo": "https://github.com/T-Crypt/berth", "license": "Apache-2.0. The Berth name, the Pilot mascot and the artwork in assets/ are excluded from the licence, per the NOTICE file", "transports": [ "http" ], "packages": [ { "registry": "go", "name": "github.com/T-Crypt/berth" } ], "auth": "api-key", "authNotes": "The gateway (`berth gateway`, 127.0.0.1:9799) takes one bearer key on every API route. The key is created on first use in `~/.config/berth/api.key` with mode 600, a group- or world-readable file is refused, `berth key` prints it, and the comparison is constant-time. The gateway binds loopback only, refuses non-loopback Host names and any request with a browser Origin. The key has no scopes and no documented rotation command. The daemon itself answers on a Unix socket with mode 600 in a 700 directory, so only the owning user can lease the card. The harbor web UI (127.0.0.1:9798) is read-only with no login, and its actions need a device paired with `berth pair`. The wake page and the optional `--comfyui-listen` port take no key by design.", "pricing": "free", "pricingNotes": "Free under Apache-2.0 with nothing to buy and no account. No hosted service.", "priceSummary": "Free · OSS", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the README, the docs or the changelog (checked 2026-10-28). Nothing is sold.", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-11-01" }, "docsUrl": "https://t-crypt.github.io/berth/", "capabilities": [ "inference.local", "compute.gpu" ], "tags": [ "open-source", "local", "self-hosted", "free", "no-card", "apache-2.0", "openai-compatible", "go", "cli", "linux", "windows", "gpu", "agent-skill", "alpha", "pre-1.0", "new" ], "lastRelease": "2026-11-01", "graded": true, "anchor": { "graded": true, "score": 64.6, "grade": "B", "agentReady": false, "rank": 461, "ranked": true, "rankOf": 1510, "categoryRank": 1, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 75, "maintenance": 76, "payments": 60, "reliability": 61, "schema": 69, "security": 51, "transparency": 68 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-01" }, "negative": 0, "verdict": "Berth coordinates one or more NVIDIA cards between engines, ComfyUI and games, grants a lease only after the driver shows memory free, and gives agents a skill, JSON output and a keyed loopback gateway. It is 21 days old, alpha and maintained by one developer, with Windows, AMD and multiple GPUs experimental and no machine-readable API spec.", "bestFor": "Someone running several GPU programs (llama.cpp, llama-swap, Ollama, vLLM, ComfyUI, games) on one NVIDIA card who wants them to take turns, and agents that need to ask for the card.", "strengths": [ "A lease is granted only after the driver shows the previous holder's memory free, and processes it did not start are reported, never killed", "Every reporting command takes `--format json|yaml`, with results on stdout and exit codes 0, 1, 2 and 75 by one documented rule", "Gateway failures return 503 with Retry-After and a machine code such as `outranked`, `engine_oom` or `no_headroom`", "CI builds, vets, lints and tests on Linux and Windows, and releases publish SHA256SUMS that `berth update` checks", "Apache-2.0, no account and no telemetry upload, with the one GitHub update check documented and switchable off" ], "weaknesses": [ "First released on 11 October 2026 and called alpha. Windows, AMD and multiple GPUs are experimental, and the gateway is a preview", "One bearer key with no scopes or documented rotation controls every gateway route, including switch and stop", "No OpenAPI file or llms.txt. The gateway's own routes are documented in Markdown with curl examples", "No SECURITY.md, security.txt or disclosure route, and the harbor has no login when bound past loopback", "Linux and NVIDIA only for full support, through nvidia-smi. Intel and Apple GPUs are not supported" ], "agentNotes": [ "Run `berth status --format json` before starting, stopping or switching any GPU engine. If berthd is unreachable, no engine is protected", "Never kill a process to free VRAM. Ask for the card with `berth run`, `berth hold` or a gateway request, and report stowaways to the user", "Send gateway requests to http://127.0.0.1:9799/v1 with `Authorization: Bearer $(berth key)`, and use `\"stream\": true` for cold starts of up to minutes", "On a 503, read the `code` and wait for `Retry-After`. A pinned holder (a game or `berth hold`) answers 409 to stop and is the user's call", "Ask the user before `berth reclaim LEASE --yes`, any berth.toml edit or `berth update`. Each changes the node" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 64.6 } ], "editorialScores": { "ergonomics": 75, "maintenance": 76, "payments": 60, "reliability": 61, "schema": 69, "security": 51, "transparency": 74 }, "provenanceScore": 61, "checked": { "categories": { "ergonomics": "2026-11-01", "maintenance": "2026-11-01", "payments": "2026-11-01", "reliability": "2026-11-01", "schema": "2026-11-01", "security": "2026-11-01", "transparency": "2026-11-01" }, "last": "2026-11-01", "lastMoved": "2026-11-01", "oldest": "2026-11-01", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "go install github.com/T-Crypt/berth/cmd/berth@latest # or a release binary checked against SHA256SUMS\nberth service install --harbor\nberth status\nberth run --as llama --priority foreground -- llama-server -m model.gguf --port 8080", "http": "curl -s http://127.0.0.1:9799/v1/berth/board -H \"Authorization: Bearer $(berth key)\"", "claudeCode": "berth skill install # writes the Berth and ComfyUI skills, including to ~/.claude/skills" }, "letme": { "capability": "https://letme.dev/inference.local", "tool": "https://letme.dev/berth" }, "area": "models", "provenance": { "legalEntity": "Trevin Tindall (T-Crypt on GitHub)", "domain": "", "domainRegistered": "", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://github.com/T-Crypt/berth/blob/main/CHANGELOG.md", "securityTxt": "none", "checked": "2026-10-28", "notes": [ "The project has no website of its own. The docs are an MkDocs site at https://t-crypt.github.io/berth/. The NOTICE and README name Trevin Tindall (T-Crypt) as the creator and maintainer, and the licence is Apache-2.0.", "No terms, privacy policy, SECURITY.md or security.txt. The changelog has a Security heading for v0.3.4.", "The software runs on the owner's machine, so there is no vendor endpoint or status page to check.", "T-Crypt/berth is the original. jenerestain/berth, sefator/berth and Bacongineer/berth-upstream keep its module path, copyright and links, and are forks of earlier snapshots." ], "score": 61 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/berth.json", "live": { "slug": "berth", "versions": [ { "registry": "github", "name": "T-Crypt/berth", "version": "v0.4.1", "released": "2026-11-01", "seenAt": "2026-11-06T23:10:44.929173839Z" } ], "githubStars": 288, "pages": [ { "url": "https://raw.githubusercontent.com/T-Crypt/berth/main/CHANGELOG.md", "kind": "changelog", "status": 304, "checkedAt": "2026-11-07T14:19:25.200705381Z", "changedAt": "2026-11-02T07:25:10.295986681Z", "fingerprint": "b257862f46d8" } ], "github": { "repo": "t-crypt/berth", "checkedAt": "2026-11-02T08:23:35.928500119Z", "stars": 272, "archived": false, "issuesEnabled": true, "pushedAt": "2026-11-02T04:50:15Z", "openIssues": 8, "openPRs": 2, "issuesOpened90d": 39, "issuesClosed90d": 31, "prsMerged90d": 244, "ci": { "branch": "main", "runs": 50, "success": 48, "failure": 2, "other": 0, "latest": "success", "latestAt": "2026-11-01T16:42:59Z" }, "replies": { "sampled": 25, "unanswered": 2, "medianDays": 0.1 } }, "updatedAt": "2026-11-07T14:19:25.200705381Z" } }, "answer": "Berth scores 64.6 (B) on agent readiness against PrivateGPT's 53.2 (D), and leads in 4 of 7 scored categories. PrivateGPT leads on reliability and schema \u0026 documentation.", "b": { "slug": "privategpt", "name": "PrivateGPT", "vendor": "Zylon (PriBAI Technology Spain S.L.)", "vendorUrl": "https://docs.privategpt.dev", "kind": "http-api", "category": "local-ai", "summary": "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.", "url": "https://www.anchorterminal.com/tools/privategpt", "markdownUrl": "https://www.anchorterminal.com/tools/privategpt.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/privategpt.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/privategpt.json", "dns": "privategpt.grade.anchorterminal.com", "repo": "https://github.com/zylon-ai/private-gpt", "license": "Apache-2.0", "transports": [ "http" ], "packages": [ { "registry": "oci", "name": "zylonai/private-gpt" } ], "auth": "none", "authNotes": "Authentication is off by default. When `server.auth.enabled` is set, every request must carry one static secret in the `Authorization` header, compared with the whole header value. There are no per-user keys, scopes or rotation, and the docs show it as a Bearer token, a Basic value and an Anthropic API key in different places (checked 2026-11-06).", "pricing": "free", "pricingNotes": "Free under Apache-2.0 with no account or card. The cost is the owner's hardware and model server. Zylon sells a separate enterprise platform built on PrivateGPT through demos, with no public price (checked 2026-11-06).", "priceSummary": "Free · OSS", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the source, the OpenAPI file or the docs (checked 2026-11-06).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 57600, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-11-06" }, "docsUrl": "https://docs.privategpt.dev/introduction", "llmsTxt": "https://docs.privategpt.dev/llms.txt", "openapi": "https://raw.githubusercontent.com/zylon-ai/private-gpt/main/fern/openapi/openapi.json", "capabilities": [ "inference.local", "memory.search", "agent.mcp-client" ], "tags": [ "open-source", "local", "self-hosted", "docker", "openapi", "llms-txt", "rag", "mcp-client", "anthropic-compatible", "python", "free" ], "lastRelease": "2026-06-18", "graded": true, "anchor": { "graded": true, "score": 53.2, "grade": "D", "agentReady": false, "rank": 960, "ranked": true, "rankOf": 1510, "categoryRank": 11, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 64, "maintenance": 41, "payments": 60, "reliability": 70, "schema": 83, "security": 32, "transparency": 64 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-06" }, "negative": -7, "negativeNotes": [ "Issue #2269, opened 11 June 2026, reports that the async ingestion API reads any local path given as a URI artifact. The stale bot closed it as not planned on 5 July with no maintainer reply, and `load_file_from_uri` in the source of 29 October 2026 still falls back to reading a local file for any value that isn't a URL, s3 or base64. With authentication off and a 0.0.0.0 bind by default, that is an open file-read path on a default install. Read from the source, not run (-7). https://github.com/zylon-ai/private-gpt/issues/2269" ], "verdict": "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.", "bestFor": "A local backend for apps and agents that want an Anthropic-style API with document retrieval, citations and tools over local models.", "strengths": [ "Messages API modelled on Anthropic's, so Claude Code and Anthropic SDKs work by changing the base URL", "OpenAPI file of 38 paths, llms.txt and Markdown copies of every docs page", "Retrieval with citations, async ingestion, web, database and tabular tools, and remote MCP servers in one API", "Apache-2.0, with no telemetry to Zylon found in the source and OpenTelemetry tracing off by default", "Works with Ollama, llama.cpp, vLLM, LM Studio or any OpenAI-compatible server" ], "weaknesses": [ "Authentication is off by default, the server binds 0.0.0.0 and CORS allows every origin", "When on, authentication is one shared static secret, with no per-user keys or scopes", "A June 2026 report of local file reads through URI artifacts was closed by a stale bot, and the source still reads local paths", "No release since 1.0.1 in June 2026 while main has moved on, including a breaking change", "Code execution runs as a host subprocess with resource limits, not in a container" ], "agentNotes": [ "Turn on `server.auth` and bind to 127.0.0.1 before exposing an instance, since a default start answers any caller", "Point Anthropic SDKs or Claude Code at the server with `ANTHROPIC_BASE_URL=http://localhost:8080`", "Start an OpenAI-compatible model server and an embedding server first, and set `OPENAI_API_BASE` and `OPENAI_EMBEDDING_API_BASE`", "Pass ingested documents through `tool_context` to get answers with citations", "Treat web fetch, search and MCP results as untrusted, since PrivateGPT documents no prompt-injection handling" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "D", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 53.2 } ], "editorialScores": { "ergonomics": 64, "maintenance": 41, "payments": 60, "reliability": 70, "schema": 83, "security": 32, "transparency": 67 }, "provenanceScore": 61, "checked": { "categories": { "ergonomics": "2026-11-06", "maintenance": "2026-11-06", "payments": "2026-11-06", "reliability": "2026-11-06", "schema": "2026-11-06", "security": "2026-11-06", "transparency": "2026-11-06" }, "last": "2026-11-06", "oldest": "2026-11-06", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "brew tap zylon-ai/tap\nbrew install private-gpt", "http": "curl http://localhost:8080/v1/messages \\\n -H \"Content-Type: application/json\" \\\n -d '{\"model\": \"qwen3.5:35b\", \"messages\": [{\"role\": \"user\", \"content\": \"Explain retrieval-augmented generation.\"}]}'" }, "letme": { "capability": "https://letme.dev/inference.local", "tool": "https://letme.dev/privategpt" }, "area": "models", "provenance": { "legalEntity": "PriBAI Technology Spain S.L.", "domain": "privategpt.dev", "domainRegistered": "2023-10-16", "endpointOnVendorDomain": null, "terms": "https://github.com/zylon-ai/private-gpt/blob/main/LICENSE", "privacy": "", "statusPage": "", "changelog": "https://github.com/zylon-ai/private-gpt/blob/main/CHANGELOG.md", "securityTxt": "none", "checked": "2026-11-06", "notes": [ "Self-hosted software with no hosted endpoint, so the Apache-2.0 licence stands in for terms and no privacy policy is scored.", "The zylon.ai terms name PriBAI Technology Spain S.L. (VAT ESB56550130) under Spanish law and cover the website and Zylon services. They forbid access through bots, scripts or scrapers, outside standard search engine or browser use. We read the terms and two public pages.", "RDAP gives privategpt.dev a registration date of 16 October 2023.", "docs.privategpt.dev/.well-known/security.txt and www.zylon.ai/.well-known/security.txt answer 404. SECURITY.md in the repository is the reporting route.", "docs.privategpt.dev and www.zylon.ai robots.txt allow our reader. wheels.privategpt.dev has no robots.txt (404)." ], "score": 61 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/privategpt.json", "live": { "slug": "privategpt", "versions": [ { "registry": "github", "name": "zylon-ai/private-gpt", "version": "v1.0.1", "released": "2026-06-18", "seenAt": "2026-11-06T23:58:40.643071731Z" } ], "githubStars": 57632, "securityTxt": { "url": "https://privategpt.dev/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-07T15:59:53.351491852Z" }, "llmsTxt": { "url": "https://docs.privategpt.dev/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-07T15:33:41.730243326Z" }, "pages": [ { "url": "https://raw.githubusercontent.com/zylon-ai/private-gpt/main/CHANGELOG.md", "kind": "changelog", "status": 200, "checkedAt": "2026-11-07T14:24:15.016082629Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "767d5dd99544" }, { "url": "https://raw.githubusercontent.com/zylon-ai/private-gpt/main/LICENSE", "kind": "terms", "status": 200, "checkedAt": "2026-11-07T14:24:17.075442465Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "839fbbcddc72" } ], "updatedAt": "2026-11-07T15:59:53.351491852Z" } }, "edges": [ { "by": 35, "category": "maintenance", "leads": "berth", "name": "Maintenance \u0026 community", "reasons": { "a": "v0.4.1 on 1 November 2026 and v0.4.0 on 29 October, per the repository's tags and the changelog (30). Eleven releases from v0.1.0 on 11 October to v0.4.1, plus nine release candidates (20). The changelog credits outside reporters and fixes their issues within days (azrael-229's #231 and #232, TacoTakumi's and cygnal's #189 and #196 in v0.4.0, and Windows testers' #81, #82, #103 and #104 fixed in releases tagged 20 and 21 October). Reply times and open issue counts were unreadable, and the project is 21 days old (18 of 25). No MCP server or official SDK (0). Go 1.27.1 with current dependencies (golang.org/x/sys 0.48.0, modernc.org/sqlite 1.60.1) and CI on both platforms, but no Dependabot or Renovate (8 of 10). 30+20+18+0+8 = 76.", "b": "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." }, "scores": { "a": 76, "b": 41 } }, { "by": 19, "category": "security", "leads": "berth", "name": "Security \u0026 auth", "reasons": { "a": "Read with the tool checklist, for the gateway and the daemon. The gateway takes one random bearer key, kept in a mode-600 file that is refused when others can read it and compared in constant time, on a loopback-only bind that refuses non-loopback Host names and browser Origins. The daemon's Unix socket is mode 600 in a 700 directory. The key has no scopes and no documented rotation, the wake page and the optional ComfyUI port take none, and the Windows control pipe is not locked down, per the support matrix (12 of 30). Berth never kills a process it did not start, stowaways are report-only, a pinned holder can't be stopped from the network (409), `berth reclaim` needs `--yes`, `berth update` asks before replacing the binary, and the harbor is read-only, with actions only for a paired device. No read-only key (15 of 20). The gateway passes model output through. The skill tells agents to ask the user before reclaiming, editing config or filing an issue, but there is no prompt-injection guidance (8 of 15). An event log with JSON output, lease records, a 24-hour request log, 30 days of history and Prometheus metrics, with no caller identity beyond the one key (11 of 15). No SECURITY.md, security.txt, bounty or advisories at v0.4.1. The changelog disclosed the v0.3.4 fix to the gateway forwarding the node's key to engines, releases carry SHA256SUMS that `berth update` checks, and `berth pull` checks Hugging Face's sha256. The linters don't include gosec (5 of 20). 12+15+8+11+5 = 51.", "b": "Read with the tool checklist. Authentication is off by default, and when on it is one static secret compared with the whole `Authorization` header, with a sample `secret:key` value in settings.yaml. There are no per-user keys or scopes, `private-gpt serve` binds 0.0.0.0 by default and CORS allows every origin, so a default start answers anyone on the network. The docs disagree on the header (Bearer, Basic or an Anthropic key) (6 of 30). Tools are chosen per request and code execution has internet off by default, but bash runs as a host subprocess with resource limits, not in a container, and nothing asks for approval (6 of 20). Web fetch, web search, documents and MCP servers bring untrusted text to the model. A public prompt-injection report (#2270) was closed by the stale bot, and no guidance was found beyond a 19 October change that bounds tool output (3 of 15). OpenTelemetry traces cover every request, model call, tool and sandbox step, off by default, with local JSON lines exporters (10 of 15). SECURITY.md since 23 July 2026 asks for private reports through GitHub or Discord. No bounty, no certification, and the June and July security reports in issues were closed by a bot with no reply (7 of 20). 6 + 6 + 3 + 10 + 7 = 32." }, "scores": { "a": 51, "b": 32 } }, { "by": 14, "category": "schema", "leads": "privategpt", "name": "Schema \u0026 documentation", "reasons": { "a": "Read with the API lines, for the gateway and the CLI's JSON output an agent uses. No OpenAPI file or JSON Schema for the gateway's own routes or the CLI output. The OpenAI-compatible routes follow OpenAI's shape and /v1/berth routes are shown with request and response JSON (6 of 25). No llms.txt (404 on the docs site). The docs are Markdown in the repository and an MkDocs site, and `berth skill install` writes SKILL.md files written for agents (8 of 10). The skill's description says when to load it, and its rules say what not to do (kill a GPU process, start an engine outside Berth, work round a pinned lease), with a docs page for each function (17 of 20). Flags and fields take documented values (priority batch, interactive, foreground, hold; format human, json, yaml; tier hot, warm, cool, cold), and `berth config check` validates the config, but nothing is typed in a schema (9 of 15). curl examples for each gateway route, eight documented 503 reason codes with Retry-After, 404, 409 and 400 cases, and the CLI's exit codes 0, 1, 2 and 75 (14 of 15). A dated changelog, semver and routes under /v1 (15). 6+8+17+9+14+15 = 69.", "b": "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." }, "scores": { "a": 69, "b": 83 } }, { "by": 11, "category": "ergonomics", "leads": "berth", "name": "Agent ergonomics", "reasons": { "a": "Read with the API lines. `--format json|yaml` on every reporting command, `-q` for an exit code alone, and `/v1/berth/board` for the whole node in one read, and since v0.4.1 a base URL per card, `/cards/CARD/v1`. The skill is about 12.9 KB at v0.4.1, loaded only when an agent picks it up (18 of 25). Queries take an engine or model (`/v1/berth/cost?engine=`, `/v1/berth/wait?model=`), the harbor picks 1H to 30D windows, and lists are small, but there is no paging or field selection (12 of 20). Wait reasons name the holder and the waiter's place in line, refusals give the memory figures, and 503s carry a machine code and Retry-After (19 of 20). Concurrent requests share one engine start, a crashing engine is not restarted on every retry (15 s doubling to 5 min), switch answers 202 and stop on a pinned holder 409, and the skill says to retry a refusal later. No idempotency keys (15 of 20). Loopback defaults, a key created on first use and read with `berth key`, and OpenAI clients work unchanged. No SDK (11 of 15). 18+12+19+15+11 = 75.", "b": "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." }, "scores": { "a": 75, "b": 64 } }, { "by": 9, "category": "reliability", "leads": "privategpt", "name": "Reliability", "reasons": { "a": "Read with the local-software lines, since Berth runs on the owner's machine with no hosted service. Static release binaries for Linux amd64 and arm64 and Windows amd64 with SHA256SUMS, built by the release workflow, and `go install`, with a support matrix in the README. No distribution package, no Windows installer, and github.com refused our reader, so the release assets themselves were not seen (18 of 20). CI builds, checks formatting, vets, lints and runs `go test ./...` on Linux and runs build, vet and tests on windows-latest, on pushes to main and next and on pull requests, over 227 test files at v0.4.1. Whether it passes on main couldn't be read, since GitHub's pages refuse us and the earlier pass reading came from a third-party badge service, which this check doesn't use (15 of 25). The changelog credits outside reporters by issue number and fixes their reports within days (Windows reports #81, #82, #103 and #104 in v0.3.2 and v0.3.3, #189, #193, #196, #231 and #232 in v0.4.0 on 29 October). Open issue counts and reply times were unreadable (15 of 25). Semver tags, a Keep a Changelog file with dated Added, Changed and Fixed sections, and a pre-release channel. Behaviour changes are explained under Changed with what to do, such as v0.4.0 governing every card by default and how to keep the old behaviour, with no Breaking heading (13 of 15). v0.4.1, called alpha (0). 18+15+15+13+0 = 61.", "b": "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." }, "scores": { "a": 61, "b": 70 } } ], "facts": [ { "a": "HTTP API", "b": "HTTP API", "name": "Kind" }, { "a": "Trevin Tindall (T-Crypt on GitHub)", "b": "Zylon (PriBAI Technology Spain S.L.)", "name": "Vendor" }, { "a": "no (local only)", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "HTTP", "b": "HTTP", "name": "Transports" }, { "a": "API key", "b": "None", "name": "Auth" }, { "a": "Free", "b": "Free", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Apache-2.0. The Berth name, the Pilot mascot and the artwork in assets/ are excluded from the licence, per the NOTICE file", "b": "Apache-2.0", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "yes", "name": "llms.txt" }, { "a": "2026-11-01", "b": "2026-06-18", "name": "Last release" }, { "a": "no document linked", "b": "no date given", "name": "Terms last updated" }, { "a": "no document linked", "b": "no document linked", "name": "Privacy policy last updated" }, { "a": "not read yet", "b": "not found in the text", "name": "Customer content may train models" }, { "a": "not read yet", "b": "not found in the text", "name": "Terms restrict automated access" }, { "a": "not read yet", "b": "not found in the text", "name": "Terms restrict benchmarking" }, { "a": "not read yet", "b": "not found in the text", "name": "Terms or service can change without notice" }, { "a": "not read yet", "b": "not found in the text", "name": "Arbitration or class-action waiver" }, { "a": "none", "b": "58k stars", "name": "Popularity" } ], "faq": [ { "answer": "Berth scores 64.6 (B) on agent readiness against PrivateGPT's 53.2 (D), and leads in 4 of 7 scored categories. PrivateGPT leads on reliability and schema \u0026 documentation.", "question": "Which is better for AI agents, Berth or PrivateGPT?" }, { "answer": "Berth needs an API key. PrivateGPT needs no key.", "question": "Do Berth and PrivateGPT need an API key?" }, { "answer": "No hosted endpoint is listed for Berth. No hosted endpoint is listed for PrivateGPT.", "question": "Can an agent call Berth and PrivateGPT without installing anything?" }, { "answer": "Yes. Berth is open source (Apache-2.0. The Berth name, the Pilot mascot and the artwork in assets/ are excluded from the licence, per the NOTICE file). PrivateGPT is open source (Apache-2.0).", "question": "Are Berth and PrivateGPT open source?" } ], "goodFor": [ { "aheadOn": [ "Agent ergonomics, 75 against 64", "Security \u0026 auth, 51 against 32", "Maintenance \u0026 community, 76 against 41" ], "also": [ "Free to start without a card", "No incidents deducted, where PrivateGPT loses 7 points for them" ], "goodFor": "Someone running several GPU programs (llama.cpp, llama-swap, Ollama, vLLM, ComfyUI, games) on one NVIDIA card who wants them to take turns, and agents that need to ask for the card.", "slug": "berth", "watchFor": "First released on 11 October 2026 and called alpha. Windows, AMD and multiple GPUs are experimental, and the gateway is a preview" }, { "aheadOn": [ "Reliability, 70 against 61", "Schema \u0026 documentation, 83 against 69" ], "also": [ "No key needed to call it" ], "goodFor": "A local backend for apps and agents that want an Anthropic-style API with document retrieval, citations and tools over local models.", "slug": "privategpt", "watchFor": "Authentication is off by default, the server binds 0.0.0.0 and CORS allows every origin" } ], "history": { "berth": [ { "causes": [ "correction" ], "date": "2026-11-01", "delta": -3, "from": 67.6, "fromGrade": "B", "to": 64.6, "toGrade": "B" } ], "privategpt": null }, "job": { "capability": "inference.local", "name": "Local inference" }, "others": [ { "json": "https://www.anchorterminal.com/compare/anythingllm-vs-berth.json", "title": "AnythingLLM vs Berth", "url": "https://www.anchorterminal.com/compare/anythingllm-vs-berth" }, { "json": "https://www.anchorterminal.com/compare/anythingllm-vs-privategpt.json", "title": "AnythingLLM vs PrivateGPT", "url": "https://www.anchorterminal.com/compare/anythingllm-vs-privategpt" }, { "json": "https://www.anchorterminal.com/compare/berth-vs-bitrun.json", "title": "Berth vs BitRun", "url": "https://www.anchorterminal.com/compare/berth-vs-bitrun" }, { "json": "https://www.anchorterminal.com/compare/berth-vs-docker-model-runner.json", "title": "Berth vs Docker Model Runner", "url": "https://www.anchorterminal.com/compare/berth-vs-docker-model-runner" }, { "json": "https://www.anchorterminal.com/compare/berth-vs-foundry-local.json", "title": "Berth vs Foundry Local", "url": "https://www.anchorterminal.com/compare/berth-vs-foundry-local" }, { "json": "https://www.anchorterminal.com/compare/berth-vs-ghost-core.json", "title": "Berth vs Core", "url": "https://www.anchorterminal.com/compare/berth-vs-ghost-core" }, { "json": "https://www.anchorterminal.com/compare/berth-vs-gpt4all.json", "title": "Berth vs GPT4All", "url": "https://www.anchorterminal.com/compare/berth-vs-gpt4all" }, { "json": "https://www.anchorterminal.com/compare/berth-vs-hyperqwen.json", "title": "Berth vs HyperQwen", "url": "https://www.anchorterminal.com/compare/berth-vs-hyperqwen" }, { "json": "https://www.anchorterminal.com/compare/berth-vs-jan.json", "title": "Berth vs Jan", "url": "https://www.anchorterminal.com/compare/berth-vs-jan" }, { "json": "https://www.anchorterminal.com/compare/berth-vs-khoj.json", "title": "Berth vs Khoj", "url": "https://www.anchorterminal.com/compare/berth-vs-khoj" }, { "json": "https://www.anchorterminal.com/compare/berth-vs-koboldcpp.json", "title": "Berth vs KoboldCpp", "url": "https://www.anchorterminal.com/compare/berth-vs-koboldcpp" }, { "json": "https://www.anchorterminal.com/compare/berth-vs-lemonade.json", "title": "Berth vs Lemonade", "url": "https://www.anchorterminal.com/compare/berth-vs-lemonade" }, { "json": "https://www.anchorterminal.com/compare/berth-vs-llama-cpp.json", "title": "Berth vs llama.cpp", "url": "https://www.anchorterminal.com/compare/berth-vs-llama-cpp" }, { "json": "https://www.anchorterminal.com/compare/berth-vs-lm-studio.json", "title": "Berth vs LM Studio", "url": "https://www.anchorterminal.com/compare/berth-vs-lm-studio" }, { "json": "https://www.anchorterminal.com/compare/berth-vs-localai.json", "title": "Berth vs LocalAI", "url": "https://www.anchorterminal.com/compare/berth-vs-localai" }, { "json": "https://www.anchorterminal.com/compare/berth-vs-mlx-lm.json", "title": "Berth vs MLX LM", "url": "https://www.anchorterminal.com/compare/berth-vs-mlx-lm" }, { "json": "https://www.anchorterminal.com/compare/berth-vs-ollama.json", "title": "Berth vs Ollama", "url": "https://www.anchorterminal.com/compare/berth-vs-ollama" }, { "json": "https://www.anchorterminal.com/compare/berth-vs-open-webui.json", "title": "Berth vs Open WebUI", "url": "https://www.anchorterminal.com/compare/berth-vs-open-webui" }, { "json": "https://www.anchorterminal.com/compare/berth-vs-screenpipe.json", "title": "Berth vs screenpipe", "url": "https://www.anchorterminal.com/compare/berth-vs-screenpipe" }, { "json": "https://www.anchorterminal.com/compare/berth-vs-text-generation-webui.json", "title": "Berth vs TextGen", "url": "https://www.anchorterminal.com/compare/berth-vs-text-generation-webui" }, { "json": "https://www.anchorterminal.com/compare/berth-vs-vllm.json", "title": "Berth vs vLLM", "url": "https://www.anchorterminal.com/compare/berth-vs-vllm" }, { "json": "https://www.anchorterminal.com/compare/bitrun-vs-privategpt.json", "title": "BitRun vs PrivateGPT", "url": "https://www.anchorterminal.com/compare/bitrun-vs-privategpt" }, { "json": "https://www.anchorterminal.com/compare/docker-model-runner-vs-privategpt.json", "title": "Docker Model Runner vs PrivateGPT", "url": "https://www.anchorterminal.com/compare/docker-model-runner-vs-privategpt" }, { "json": "https://www.anchorterminal.com/compare/foundry-local-vs-privategpt.json", "title": "Foundry Local vs PrivateGPT", "url": "https://www.anchorterminal.com/compare/foundry-local-vs-privategpt" }, { "json": "https://www.anchorterminal.com/compare/ghost-core-vs-privategpt.json", "title": "Core vs PrivateGPT", "url": "https://www.anchorterminal.com/compare/ghost-core-vs-privategpt" }, { "json": "https://www.anchorterminal.com/compare/gpt4all-vs-privategpt.json", "title": "GPT4All vs PrivateGPT", "url": "https://www.anchorterminal.com/compare/gpt4all-vs-privategpt" }, { "json": "https://www.anchorterminal.com/compare/hyperqwen-vs-privategpt.json", "title": "HyperQwen vs PrivateGPT", "url": "https://www.anchorterminal.com/compare/hyperqwen-vs-privategpt" }, { "json": "https://www.anchorterminal.com/compare/jan-vs-privategpt.json", "title": "Jan vs PrivateGPT", "url": "https://www.anchorterminal.com/compare/jan-vs-privategpt" }, { "json": "https://www.anchorterminal.com/compare/koboldcpp-vs-privategpt.json", "title": "KoboldCpp vs PrivateGPT", "url": "https://www.anchorterminal.com/compare/koboldcpp-vs-privategpt" }, { "json": "https://www.anchorterminal.com/compare/lemonade-vs-privategpt.json", "title": "Lemonade vs PrivateGPT", "url": "https://www.anchorterminal.com/compare/lemonade-vs-privategpt" }, { "json": "https://www.anchorterminal.com/compare/llama-cpp-vs-privategpt.json", "title": "llama.cpp vs PrivateGPT", "url": "https://www.anchorterminal.com/compare/llama-cpp-vs-privategpt" }, { "json": "https://www.anchorterminal.com/compare/lm-studio-vs-privategpt.json", "title": "LM Studio vs PrivateGPT", "url": "https://www.anchorterminal.com/compare/lm-studio-vs-privategpt" }, { "json": "https://www.anchorterminal.com/compare/localai-vs-privategpt.json", "title": "LocalAI vs PrivateGPT", "url": "https://www.anchorterminal.com/compare/localai-vs-privategpt" }, { "json": "https://www.anchorterminal.com/compare/mlx-lm-vs-privategpt.json", "title": "MLX LM vs PrivateGPT", "url": "https://www.anchorterminal.com/compare/mlx-lm-vs-privategpt" }, { "json": "https://www.anchorterminal.com/compare/ollama-vs-privategpt.json", "title": "Ollama vs PrivateGPT", "url": "https://www.anchorterminal.com/compare/ollama-vs-privategpt" }, { "json": "https://www.anchorterminal.com/compare/open-webui-vs-privategpt.json", "title": "Open WebUI vs PrivateGPT", "url": "https://www.anchorterminal.com/compare/open-webui-vs-privategpt" }, { "json": "https://www.anchorterminal.com/compare/privategpt-vs-screenpipe.json", "title": "PrivateGPT vs screenpipe", "url": "https://www.anchorterminal.com/compare/privategpt-vs-screenpipe" }, { "json": "https://www.anchorterminal.com/compare/privategpt-vs-text-generation-webui.json", "title": "PrivateGPT vs TextGen", "url": "https://www.anchorterminal.com/compare/privategpt-vs-text-generation-webui" }, { "json": "https://www.anchorterminal.com/compare/privategpt-vs-vllm.json", "title": "PrivateGPT vs vLLM", "url": "https://www.anchorterminal.com/compare/privategpt-vs-vllm" }, { "json": "https://www.anchorterminal.com/compare/khoj-vs-privategpt.json", "title": "Khoj vs PrivateGPT", "url": "https://www.anchorterminal.com/compare/khoj-vs-privategpt" }, { "json": "https://www.anchorterminal.com/compare/localghost-vs-privategpt.json", "title": "LocalGhost vs PrivateGPT", "url": "https://www.anchorterminal.com/compare/localghost-vs-privategpt" } ], "panel": null, "scores": [ { "berth": 61, "by": 9, "edge": "privategpt", "key": "reliability", "name": "Reliability", "privategpt": 70, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "berth": 69, "by": 14, "edge": "privategpt", "key": "schema", "name": "Schema \u0026 documentation", "privategpt": 83, "weight": 13 }, { "berth": 75, "by": 11, "edge": "berth", "key": "ergonomics", "name": "Agent ergonomics", "privategpt": 64, "weight": 13 }, { "berth": 51, "by": 19, "edge": "berth", "key": "security", "name": "Security \u0026 auth", "privategpt": 32, "weight": 14 }, { "berth": 60, "by": 0, "edge": "", "key": "payments", "name": "Payments \u0026 pricing", "privategpt": 60, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "berth": 76, "by": 35, "edge": "berth", "key": "maintenance", "name": "Maintenance \u0026 community", "privategpt": 41, "weight": 7 }, { "berth": 68, "by": 4, "edge": "berth", "key": "transparency", "name": "Transparency \u0026 trust", "privategpt": 64, "weight": 7 } ], "summary": "Berth scores 64.6 (B) on agent readiness against PrivateGPT's 53.2 (D), and leads in 4 of 7 scored categories. PrivateGPT leads on reliability and schema \u0026 documentation. Both do local inference.", "tasks": null, "tutorials": [], "verdicts": { "berth": "Berth coordinates one or more NVIDIA cards between engines, ComfyUI and games, grants a lease only after the driver shows memory free, and gives agents a skill, JSON output and a keyed loopback gateway. It is 21 days old, alpha and maintained by one developer, with Windows, AMD and multiple GPUs experimental and no machine-readable API spec.", "privategpt": "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." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/berth-vs-privategpt", "json": "https://www.anchorterminal.com/compare/berth-vs-privategpt.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/berth-vs-privategpt.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/berth-vs-privategpt.min.md" }, "markdown": "Berth scores 64.6 (B) on agent readiness against PrivateGPT's 53.2 (D), and leads in 4 of 7 scored categories. PrivateGPT leads on reliability and schema \u0026 documentation. Both do local inference.\n\n- Berth: grade B, 64.6/100, rank #461 of 1510. Markdown https://www.anchorterminal.com/tools/berth.md · JSON https://www.anchorterminal.com/api/v1/tools/berth.json\n- PrivateGPT: grade D, 53.2/100, rank #960 of 1510. Markdown https://www.anchorterminal.com/tools/privategpt.md · JSON https://www.anchorterminal.com/api/v1/tools/privategpt.json\n- Best local AI models and assistants: https://www.anchorterminal.com/best/local-ai/index.md\n- All 280 local ai comparisons: https://www.anchorterminal.com/compare/local-ai/index.md\n\n## Which one, for what\n\n### Berth (B)\n\nGood for: Someone running several GPU programs (llama.cpp, llama-swap, Ollama, vLLM, ComfyUI, games) on one NVIDIA card who wants them to take turns, and agents that need to ask for the card.\n\nAhead on:\n- Agent ergonomics, 75 against 64\n- Security \u0026 auth, 51 against 32\n- Maintenance \u0026 community, 76 against 41\n\nAlso in its favour:\n- Free to start without a card\n- No incidents deducted, where PrivateGPT loses 7 points for them\n\nWatch for: First released on 11 October 2026 and called alpha. Windows, AMD and multiple GPUs are experimental, and the gateway is a preview\n\n### PrivateGPT (D)\n\nGood for: A local backend for apps and agents that want an Anthropic-style API with document retrieval, citations and tools over local models.\n\nAhead on:\n- Reliability, 70 against 61\n- Schema \u0026 documentation, 83 against 69\n\nAlso in its favour:\n- No key needed to call it\n\nWatch for: Authentication is off by default, the server binds 0.0.0.0 and CORS allows every origin\n\n\n## Why the edge\n\n### Maintenance \u0026 community: Berth +35\n\n- Berth (76): v0.4.1 on 1 November 2026 and v0.4.0 on 29 October, per the repository's tags and the changelog (30). Eleven releases from v0.1.0 on 11 October to v0.4.1, plus nine release candidates (20). The changelog credits outside reporters and fixes their issues within days (azrael-229's #231 and #232, TacoTakumi's and cygnal's #189 and #196 in v0.4.0, and Windows testers' #81, #82, #103 and #104 fixed in releases tagged 20 and 21 October). Reply times and open issue counts were unreadable, and the project is 21 days old (18 of 25). No MCP server or official SDK (0). Go 1.27.1 with current dependencies (golang.org/x/sys 0.48.0, modernc.org/sqlite 1.60.1) and CI on both platforms, but no Dependabot or Renovate (8 of 10). 30+20+18+0+8 = 76.\n- 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.\n\n### Security \u0026 auth: Berth +19\n\n- Berth (51): Read with the tool checklist, for the gateway and the daemon. The gateway takes one random bearer key, kept in a mode-600 file that is refused when others can read it and compared in constant time, on a loopback-only bind that refuses non-loopback Host names and browser Origins. The daemon's Unix socket is mode 600 in a 700 directory. The key has no scopes and no documented rotation, the wake page and the optional ComfyUI port take none, and the Windows control pipe is not locked down, per the support matrix (12 of 30). Berth never kills a process it did not start, stowaways are report-only, a pinned holder can't be stopped from the network (409), `berth reclaim` needs `--yes`, `berth update` asks before replacing the binary, and the harbor is read-only, with actions only for a paired device. No read-only key (15 of 20). The gateway passes model output through. The skill tells agents to ask the user before reclaiming, editing config or filing an issue, but there is no prompt-injection guidance (8 of 15). An event log with JSON output, lease records, a 24-hour request log, 30 days of history and Prometheus metrics, with no caller identity beyond the one key (11 of 15). No SECURITY.md, security.txt, bounty or advisories at v0.4.1. The changelog disclosed the v0.3.4 fix to the gateway forwarding the node's key to engines, releases carry SHA256SUMS that `berth update` checks, and `berth pull` checks Hugging Face's sha256. The linters don't include gosec (5 of 20). 12+15+8+11+5 = 51.\n- PrivateGPT (32): Read with the tool checklist. Authentication is off by default, and when on it is one static secret compared with the whole `Authorization` header, with a sample `secret:key` value in settings.yaml. There are no per-user keys or scopes, `private-gpt serve` binds 0.0.0.0 by default and CORS allows every origin, so a default start answers anyone on the network. The docs disagree on the header (Bearer, Basic or an Anthropic key) (6 of 30). Tools are chosen per request and code execution has internet off by default, but bash runs as a host subprocess with resource limits, not in a container, and nothing asks for approval (6 of 20). Web fetch, web search, documents and MCP servers bring untrusted text to the model. A public prompt-injection report (#2270) was closed by the stale bot, and no guidance was found beyond a 19 October change that bounds tool output (3 of 15). OpenTelemetry traces cover every request, model call, tool and sandbox step, off by default, with local JSON lines exporters (10 of 15). SECURITY.md since 23 July 2026 asks for private reports through GitHub or Discord. No bounty, no certification, and the June and July security reports in issues were closed by a bot with no reply (7 of 20). 6 + 6 + 3 + 10 + 7 = 32.\n\n### Schema \u0026 documentation: PrivateGPT +14\n\n- Berth (69): Read with the API lines, for the gateway and the CLI's JSON output an agent uses. No OpenAPI file or JSON Schema for the gateway's own routes or the CLI output. The OpenAI-compatible routes follow OpenAI's shape and /v1/berth routes are shown with request and response JSON (6 of 25). No llms.txt (404 on the docs site). The docs are Markdown in the repository and an MkDocs site, and `berth skill install` writes SKILL.md files written for agents (8 of 10). The skill's description says when to load it, and its rules say what not to do (kill a GPU process, start an engine outside Berth, work round a pinned lease), with a docs page for each function (17 of 20). Flags and fields take documented values (priority batch, interactive, foreground, hold; format human, json, yaml; tier hot, warm, cool, cold), and `berth config check` validates the config, but nothing is typed in a schema (9 of 15). curl examples for each gateway route, eight documented 503 reason codes with Retry-After, 404, 409 and 400 cases, and the CLI's exit codes 0, 1, 2 and 75 (14 of 15). A dated changelog, semver and routes under /v1 (15). 6+8+17+9+14+15 = 69.\n- 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.\n\n### Agent ergonomics: Berth +11\n\n- Berth (75): Read with the API lines. `--format json|yaml` on every reporting command, `-q` for an exit code alone, and `/v1/berth/board` for the whole node in one read, and since v0.4.1 a base URL per card, `/cards/CARD/v1`. The skill is about 12.9 KB at v0.4.1, loaded only when an agent picks it up (18 of 25). Queries take an engine or model (`/v1/berth/cost?engine=`, `/v1/berth/wait?model=`), the harbor picks 1H to 30D windows, and lists are small, but there is no paging or field selection (12 of 20). Wait reasons name the holder and the waiter's place in line, refusals give the memory figures, and 503s carry a machine code and Retry-After (19 of 20). Concurrent requests share one engine start, a crashing engine is not restarted on every retry (15 s doubling to 5 min), switch answers 202 and stop on a pinned holder 409, and the skill says to retry a refusal later. No idempotency keys (15 of 20). Loopback defaults, a key created on first use and read with `berth key`, and OpenAI clients work unchanged. No SDK (11 of 15). 18+12+19+15+11 = 75.\n- 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.\n\n### Reliability: PrivateGPT +9\n\n- Berth (61): Read with the local-software lines, since Berth runs on the owner's machine with no hosted service. Static release binaries for Linux amd64 and arm64 and Windows amd64 with SHA256SUMS, built by the release workflow, and `go install`, with a support matrix in the README. No distribution package, no Windows installer, and github.com refused our reader, so the release assets themselves were not seen (18 of 20). CI builds, checks formatting, vets, lints and runs `go test ./...` on Linux and runs build, vet and tests on windows-latest, on pushes to main and next and on pull requests, over 227 test files at v0.4.1. Whether it passes on main couldn't be read, since GitHub's pages refuse us and the earlier pass reading came from a third-party badge service, which this check doesn't use (15 of 25). The changelog credits outside reporters by issue number and fixes their reports within days (Windows reports #81, #82, #103 and #104 in v0.3.2 and v0.3.3, #189, #193, #196, #231 and #232 in v0.4.0 on 29 October). Open issue counts and reply times were unreadable (15 of 25). Semver tags, a Keep a Changelog file with dated Added, Changed and Fixed sections, and a pre-release channel. Behaviour changes are explained under Changed with what to do, such as v0.4.0 governing every card by default and how to keep the old behaviour, with no Breaking heading (13 of 15). v0.4.1, called alpha (0). 18+15+15+13+0 = 61.\n- 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.\n\n## Score by category\n\n| Category | Weight | Berth | PrivateGPT | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 61 | 70 | PrivateGPT +9 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 69 | 83 | PrivateGPT +14 |\n| Agent ergonomics | 13% (16.2 this run) | 75 | 64 | Berth +11 |\n| Security \u0026 auth | 14% (17.5 this run) | 51 | 32 | Berth +19 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 60 | 60 | even |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 76 | 41 | Berth +35 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 68 | 64 | Berth +4 |\n| Negative events | ≤15 | 0 | -7 | |\n| **Total** | | **64.6 · B** | **53.2 · D** | |\n\n## Facts side by side\n\n| Fact | Berth | PrivateGPT |\n| --- | --- | --- |\n| Kind | HTTP API | HTTP API |\n| Vendor | Trevin Tindall (T-Crypt on GitHub) | Zylon (PriBAI Technology Spain S.L.) |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports | HTTP | HTTP |\n| Auth | API key | None |\n| Pricing | Free | Free |\n| x402 | no | no |\n| Licence | Apache-2.0. The Berth name, the Pilot mascot and the artwork in assets/ are excluded from the licence, per the NOTICE file | Apache-2.0 |\n| Read-only variant documented | no | no |\n| llms.txt | no | yes |\n| Last release | 2026-11-01 | 2026-06-18 |\n| Terms last updated | no document linked | no date given |\n| Privacy policy last updated | no document linked | no document linked |\n| Customer content may train models | not read yet | not found in the text |\n| Terms restrict automated access | not read yet | not found in the text |\n| Terms restrict benchmarking | not read yet | not found in the text |\n| Terms or service can change without notice | not read yet | not found in the text |\n| Arbitration or class-action waiver | not read yet | not found in the text |\n| Popularity | none | 58k stars |\n\n## How the scores have moved\n\n### Berth\n\n- -3.0 on 1 November 2026: correction\n\n### PrivateGPT\n\nNo score change since it was listed.\n\n## Verdicts\n\n**Berth.** Berth coordinates one or more NVIDIA cards between engines, ComfyUI and games, grants a lease only after the driver shows memory free, and gives agents a skill, JSON output and a keyed loopback gateway. It is 21 days old, alpha and maintained by one developer, with Windows, AMD and multiple GPUs experimental and no machine-readable API spec.\n\n**PrivateGPT.** 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.\n\n## Before you call either\n\n### Berth\n\n1. Run `berth status --format json` before starting, stopping or switching any GPU engine. If berthd is unreachable, no engine is protected\n2. Never kill a process to free VRAM. Ask for the card with `berth run`, `berth hold` or a gateway request, and report stowaways to the user\n3. Send gateway requests to http://127.0.0.1:9799/v1 with `Authorization: Bearer $(berth key)`, and use `\"stream\": true` for cold starts of up to minutes\n4. On a 503, read the `code` and wait for `Retry-After`. A pinned holder (a game or `berth hold`) answers 409 to stop and is the user's call\n5. Ask the user before `berth reclaim LEASE --yes`, any berth.toml edit or `berth update`. Each changes the node\n\n### PrivateGPT\n\n1. Turn on `server.auth` and bind to 127.0.0.1 before exposing an instance, since a default start answers any caller\n2. Point Anthropic SDKs or Claude Code at the server with `ANTHROPIC_BASE_URL=http://localhost:8080`\n3. Start an OpenAI-compatible model server and an embedding server first, and set `OPENAI_API_BASE` and `OPENAI_EMBEDDING_API_BASE`\n4. Pass ingested documents through `tool_context` to get answers with citations\n5. Treat web fetch, search and MCP results as untrusted, since PrivateGPT documents no prompt-injection handling\n\n## Questions\n\n### Which is better for AI agents, Berth or PrivateGPT?\n\nBerth scores 64.6 (B) on agent readiness against PrivateGPT's 53.2 (D), and leads in 4 of 7 scored categories. PrivateGPT leads on reliability and schema \u0026 documentation.\n\n### Do Berth and PrivateGPT need an API key?\n\nBerth needs an API key. PrivateGPT needs no key.\n\n### Can an agent call Berth and PrivateGPT without installing anything?\n\nNo hosted endpoint is listed for Berth. No hosted endpoint is listed for PrivateGPT.\n\n### Are Berth and PrivateGPT open source?\n\nYes. Berth is open source (Apache-2.0. The Berth name, the Pilot mascot and the artwork in assets/ are excluded from the licence, per the NOTICE file). PrivateGPT is open source (Apache-2.0).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/berth-vs-privategpt.json, and with the fewest tokens: https://www.anchorterminal.com/compare/berth-vs-privategpt.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"berth\", \"b\": \"privategpt\"}`. From a terminal: `anchor compare berth privategpt`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/berth.json and https://www.anchorterminal.com/api/v1/tools/privategpt.json\n\n## Other comparisons with Berth or PrivateGPT\n\n- [AnythingLLM vs Berth](https://www.anchorterminal.com/compare/anythingllm-vs-berth.md)\n- [AnythingLLM vs PrivateGPT](https://www.anchorterminal.com/compare/anythingllm-vs-privategpt.md)\n- [Berth vs BitRun](https://www.anchorterminal.com/compare/berth-vs-bitrun.md)\n- [Berth vs Docker Model Runner](https://www.anchorterminal.com/compare/berth-vs-docker-model-runner.md)\n- [Berth vs Foundry Local](https://www.anchorterminal.com/compare/berth-vs-foundry-local.md)\n- [Berth vs Core](https://www.anchorterminal.com/compare/berth-vs-ghost-core.md)\n- [Berth vs GPT4All](https://www.anchorterminal.com/compare/berth-vs-gpt4all.md)\n- [Berth vs HyperQwen](https://www.anchorterminal.com/compare/berth-vs-hyperqwen.md)\n- [Berth vs Jan](https://www.anchorterminal.com/compare/berth-vs-jan.md)\n- [Berth vs Khoj](https://www.anchorterminal.com/compare/berth-vs-khoj.md)\n- [Berth vs KoboldCpp](https://www.anchorterminal.com/compare/berth-vs-koboldcpp.md)\n- [Berth vs Lemonade](https://www.anchorterminal.com/compare/berth-vs-lemonade.md)\n- [Berth vs llama.cpp](https://www.anchorterminal.com/compare/berth-vs-llama-cpp.md)\n- [Berth vs LM Studio](https://www.anchorterminal.com/compare/berth-vs-lm-studio.md)\n- [Berth vs LocalAI](https://www.anchorterminal.com/compare/berth-vs-localai.md)\n- [Berth vs MLX LM](https://www.anchorterminal.com/compare/berth-vs-mlx-lm.md)\n- [Berth vs Ollama](https://www.anchorterminal.com/compare/berth-vs-ollama.md)\n- [Berth vs Open WebUI](https://www.anchorterminal.com/compare/berth-vs-open-webui.md)\n- [Berth vs screenpipe](https://www.anchorterminal.com/compare/berth-vs-screenpipe.md)\n- [Berth vs TextGen](https://www.anchorterminal.com/compare/berth-vs-text-generation-webui.md)\n- [Berth vs vLLM](https://www.anchorterminal.com/compare/berth-vs-vllm.md)\n- [BitRun vs PrivateGPT](https://www.anchorterminal.com/compare/bitrun-vs-privategpt.md)\n- [Docker Model Runner vs PrivateGPT](https://www.anchorterminal.com/compare/docker-model-runner-vs-privategpt.md)\n- [Foundry Local vs PrivateGPT](https://www.anchorterminal.com/compare/foundry-local-vs-privategpt.md)\n- [Core vs PrivateGPT](https://www.anchorterminal.com/compare/ghost-core-vs-privategpt.md)\n- [GPT4All vs PrivateGPT](https://www.anchorterminal.com/compare/gpt4all-vs-privategpt.md)\n- [HyperQwen vs PrivateGPT](https://www.anchorterminal.com/compare/hyperqwen-vs-privategpt.md)\n- [Jan vs PrivateGPT](https://www.anchorterminal.com/compare/jan-vs-privategpt.md)\n- [KoboldCpp vs PrivateGPT](https://www.anchorterminal.com/compare/koboldcpp-vs-privategpt.md)\n- [Lemonade vs PrivateGPT](https://www.anchorterminal.com/compare/lemonade-vs-privategpt.md)\n- [llama.cpp vs PrivateGPT](https://www.anchorterminal.com/compare/llama-cpp-vs-privategpt.md)\n- [LM Studio vs PrivateGPT](https://www.anchorterminal.com/compare/lm-studio-vs-privategpt.md)\n- [LocalAI vs PrivateGPT](https://www.anchorterminal.com/compare/localai-vs-privategpt.md)\n- [MLX LM vs PrivateGPT](https://www.anchorterminal.com/compare/mlx-lm-vs-privategpt.md)\n- [Ollama vs PrivateGPT](https://www.anchorterminal.com/compare/ollama-vs-privategpt.md)\n- [Open WebUI vs PrivateGPT](https://www.anchorterminal.com/compare/open-webui-vs-privategpt.md)\n- [PrivateGPT vs screenpipe](https://www.anchorterminal.com/compare/privategpt-vs-screenpipe.md)\n- [PrivateGPT vs TextGen](https://www.anchorterminal.com/compare/privategpt-vs-text-generation-webui.md)\n- [PrivateGPT vs vLLM](https://www.anchorterminal.com/compare/privategpt-vs-vllm.md)\n- [Khoj vs PrivateGPT](https://www.anchorterminal.com/compare/khoj-vs-privategpt.md)\n- [LocalGhost vs PrivateGPT](https://www.anchorterminal.com/compare/localghost-vs-privategpt.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-11-07", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.7", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run", "terms": "https://www.anchorterminal.com/terms/#data" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Berth vs PrivateGPT", "url": "" } ], "description": "Berth scores 64.6 (B) to PrivateGPT's 53.2 (D) for local inference. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Berth B 64.6", "PrivateGPT D 53.2", "scores" ], "h1": "Berth vs PrivateGPT", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/berth-vs-privategpt", "published": "2026-10-01", "section": "tools", "title": "Berth vs PrivateGPT for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-11-07", "url": "https://www.anchorterminal.com/compare/berth-vs-privategpt" }, "tokens": { "markdown": 5600, "slim": 3430 }, "version": 1 }