{ "data": { "a": { "slug": "bitrun", "name": "BitRun", "vendor": "Abhishek Khanra (IshekKhal on GitHub)", "vendorUrl": "https://github.com/IshekKhal", "kind": "http-api", "category": "local-ai", "summary": "BitRun is an open-source command-line runner for 1-bit and 1.58-bit ternary language models such as BitNet b1.58, Falcon3 1.58-bit and Bonsai on CPUs, with a model downloader and a local OpenAI-compatible server.", "url": "https://www.anchorterminal.com/tools/bitrun", "markdownUrl": "https://www.anchorterminal.com/tools/bitrun.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/bitrun.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/bitrun.json", "repo": "https://github.com/IshekKhal/bitrun", "license": "MIT", "transports": [ "http" ], "packages": [], "auth": "none", "authNotes": "No credential. `bitrun serve` starts a patched llama-server on 127.0.0.1 (default port 11435, changed with `--port`) and passes no `--api-key`, so any process on the machine can call it. The bind address is fixed in the code, with no flag to expose it on the network. The README's SDK example sets `api_key` to any string.", "pricing": "free", "pricingNotes": "Free under MIT with nothing to buy. Models are downloaded from Hugging Face under each model's own licence.", "priceSummary": "Free · OSS", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the source, the README or the release notes (checked 2026-10-15). Nothing is sold.", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 5, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-15" }, "docsUrl": "https://github.com/IshekKhal/bitrun#readme", "capabilities": [ "inference.local", "inference.open-weights" ], "tags": [ "open-source", "local", "self-hosted", "free", "no-card", "mit", "openai-compatible", "go", "pre-1.0", "macos", "windows", "cli" ], "lastRelease": "2026-10-15", "graded": true, "anchor": { "graded": true, "score": 37.9, "grade": "F", "agentReady": false, "rank": 1018, "ranked": true, "rankOf": 1094, "categoryRank": 18, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 40, "maintenance": 59, "payments": 60, "reliability": 38, "schema": 30, "security": 28, "transparency": 50 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-15" }, "negative": -3, "negativeNotes": [ "Misleading claim, 15 October 2026. The README's \"Verified Hardware Benchmarks\", described as physical hardware runs, list package power of 11.70 W, 22.60 W and 8.50 W for every model on each machine, and joules per token from them. These equal the fixed estimates in power.go (2.5 + 1.15 per thread on macOS without battery data, 5.0 + 2.2 per thread on Windows, 4.5 + 2.0 per thread on Linux without RAPL) at the default thread counts of 8, 8 and 2. The README also says Windows power is measured through PPM and that `pull` resumes downloads, and the source does neither (https://github.com/IshekKhal/bitrun/blob/0fec65a/pkg/telemetry/power.go#L137-L163, https://github.com/IshekKhal/bitrun/blob/0fec65a/pkg/models/downloader.go#L57-L60, https://github.com/IshekKhal/bitrun/blob/0fec65a/README.md). Judgement call, -3." ], "verdict": "BitRun packages patched llama.cpp builds for ternary models into one download for macOS on Apple silicon, Windows and Linux, with a loopback-only OpenAI-compatible server. It is three days old with three pre-release versions, one maintainer and no CI, and its published power figures come from a fixed formula rather than measurement.", "bestFor": "A developer who wants to try ternary models on a laptop CPU behind an OpenAI-style endpoint without building bitnet.cpp.", "strengths": [ "One archive per platform (macOS arm64, Linux amd64, Windows amd64) with llama-server, so no compiler, Python or Docker is needed", "The server binds 127.0.0.1 with no flag to expose it, and works with OpenAI SDKs by changing the base URL", "A catalogue of six ternary and compact models, 79 MB to 2.08 GB, pulled from their Hugging Face repositories by tag", "MIT licence, and no network telemetry found in the Go source. Outbound calls are model downloads on `pull`" ], "weaknesses": [ "First released on 12 October 2026. Three pre-release versions in four days, one maintainer and no CI workflow", "The README's package power and joules-per-token figures match a fixed per-thread formula in the code, not a counter reading", "No API key option, so any local process can call the server, and model downloads and the installer verify no checksum", "The server documentation covers one route, `/v1/chat/completions`, with no error responses, OpenAPI file or llms.txt", "Context windows of the catalogue models run from 768 to 8,192 tokens, and one server process serves one model" ], "agentNotes": [ "Ask the user to install BitRun and run `bitrun pull \u003ctag\u003e` and `bitrun serve \u003ctag\u003e` first. Then call http://127.0.0.1:11435/v1 with any API key string", "Poll `/health` before the first request. The server loads the model in the background and answers only when ready", "Use a model tag from the catalogue (bitnet-70m, bonsai-1.7b, falcon3-1b, bitnet-2b, falcon3-3b, bonsai-8b) and keep prompts within its context window", "Treat the README's energy figures as estimates, and don't report them as measured power", "Expect small research checkpoints. Check outputs before relying on them for code or facts" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "F", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 37.9 } ], "editorialScores": { "ergonomics": 40, "maintenance": 59, "payments": 60, "reliability": 38, "schema": 30, "security": 28, "transparency": 46 }, "provenanceScore": 53 }, "connect": { "install": "curl -fsSL https://raw.githubusercontent.com/IshekKhal/bitrun/main/install.sh | sh\nbitrun pull falcon3-1b\nbitrun serve falcon3-1b --port 11435", "http": "curl -s http://127.0.0.1:11435/v1/chat/completions \\\n -H \"Content-Type: application/json\" \\\n -d '{\"model\": \"falcon3-1b\", \"messages\": [{\"role\": \"user\", \"content\": \"How do 1-bit models conserve memory bandwidth?\"}], \"temperature\": 0.2}'" }, "letme": { "capability": "https://letme.dev/inference.local", "tool": "https://letme.dev/bitrun" }, "area": "models", "provenance": { "legalEntity": "Abhishek Khanra (IshekKhal on GitHub)", "domain": "", "domainRegistered": "", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://github.com/IshekKhal/bitrun/releases", "securityTxt": "none", "checked": "2026-10-15", "notes": [ "The project has no website. The GitHub account IshekKhal (created 17 December 2024) gives the name Abhishek Khanra, and the licence reads Copyright (c) 2026 Abhishek. The Show HN post was made by the HN account ishekofficial.", "No terms, privacy policy, SECURITY.md or security.txt. The repository has no .github folder.", "The software runs on the owner's machine, so there is no vendor endpoint or status page to check." ], "score": 53 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/bitrun.json" }, "answer": "BitRun scores 37.9 (F) on agent readiness against Underdog's 29.5 (F), and leads in 6 of 7 scored categories.", "b": { "slug": "underdog", "name": "Underdog", "vendor": "Conway Research", "vendorUrl": "https://underdog.ai", "kind": "platform", "category": "local-ai", "summary": "A personal AI from Conway Research that runs on the owner's Mac with Apple silicon.", "url": "https://www.anchorterminal.com/tools/underdog", "markdownUrl": "https://www.anchorterminal.com/tools/underdog.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/underdog.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/underdog.json", "license": "Model weights Apache-2.0 on Hugging Face (Underdog 27B 1.0 and its ternary build, Woof 4B and 2B 1.1, Bark 0.8B 1.0); woof-1.0-4B carries the Apache-2.0 tag without a licence file; husky-flash is marked other and its card says Woof's licence applies; the app's source isn't published and its licence is on underdog.ai, unchecked", "transports": [], "packages": [], "auth": "none", "authNotes": "No API, MCP server, CLI or credential for agents from Conway found as of 3 October 2026. The husky-flash card names `husky serve --model ConwayResearch/husky-flash` from an \"Underdog Greyhound repository\" that isn't public, with no port or protocol documented. Conway's 27B cards run the weights through Inco AI's Splash, which listens on `127.0.0.1:8000` with an OpenAI-compatible API and no authentication unless `--api-key` is set. The weights download from Hugging Face without a gate, though the 27B card says to run `hf auth login` first. underdog.ai, whose robots.txt refuses our reader, is unchecked.", "pricing": "free", "pricingNotes": "Free. Underdog's pricing page says \"100% free\", \"Free forever? Yes. It's your computer doing the work\" and \"There is nothing to bill you for\", with no paid tier (text supplied on 3 October 2026, because underdog.ai refuses our reader). The model weights are free Apache-2.0 downloads on Hugging Face with no login or card. The page links a sign-in, and whether the app needs an account is unchecked.", "priceSummary": "Free", "where": "local", "x402": { "level": "no", "evidence": "No payment protocol on conway.tech, husky.underdog.ai, Conway's Hugging Face organisation or its GitHub repositories (3 October 2026); underdog.ai unchecked.", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-03" }, "capabilities": [ "inference.open-weights", "speech.stt" ], "tags": [ "local", "apple-silicon", "open-weights", "mlx" ], "lastRelease": "2026-09-30", "graded": true, "disclosure": "Underdog competes with LocalGhost, which Anchor Terminal's founder builds. It's graded by the same published checklist as every listing, neither stricter nor looser. Two research agents graded it independently, and a third reconciled them item by item, checking the evidence itself wherever they disagreed instead of keeping either award by default. underdog.ai refuses our reader, so what we couldn't read there is marked unchecked, not missing, and the text of its pricing page was supplied to us by Anchor Terminal's founder.", "competesWith": "localghost", "anchor": { "graded": true, "score": 29.5, "grade": "F", "agentReady": false, "rank": 1040, "ranked": true, "rankOf": 1094, "categoryRank": 20, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 15, "maintenance": 56, "payments": 60, "reliability": 33, "schema": 24, "security": 14, "transparency": 19 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "low", "date": "2026-10-03" }, "negative": 0, "verdict": "Apache-2.0 weights on Hugging Face for Underdog 27B 1.0, Woof 4B and 2B 1.1 and Bark 0.8B 1.0, with no gate. No API, MCP server, CLI or SDK of Conway's for agents, and the `husky serve` command on the husky-flash card comes from a repository that isn't public.", "bestFor": "An owner who wants a Mac assistant over their own mail and calendar that, per Conway, keeps everything on the machine.", "disclosure": "Underdog competes with LocalGhost, which Anchor Terminal's founder builds. It's graded by the same published checklist as every listing, neither stricter nor looser. Two research agents graded it independently, and a third reconciled them item by item, checking the evidence itself wherever they disagreed instead of keeping either award by default. underdog.ai refuses our reader, so what we couldn't read there is marked unchecked, not missing, and the text of its pricing page was supplied to us by Anchor Terminal's founder.", "strengths": [ "Apache-2.0 weights on Hugging Face for Underdog 27B 1.0, Woof 4B and 2B 1.1 and Bark 0.8B 1.0, with no gate", "Eight Underdog model repositories published between 4 and 30 September 2026, the latest Underdog 27B 1.0 and a 2-bit ternary build on 30 September", "Woof 4B and 2B 1.1 ship release-provenance.json with a byte count and SHA-256 for every file", "Husky's speed post names its hardware, macOS and MLX versions and method, and publishes its weaker results too (1.02 to 1.27 times MLX on writing)", "The 27B weights run outside the app through Splash's OpenAI-compatible API, per Conway's ternary card" ], "weaknesses": [ "No API, MCP server, CLI or SDK of Conway's for agents, and the `husky serve` command on the husky-flash card comes from a repository that isn't public", "The app's source isn't published, and none of Conway's three public GitHub repositories mentions Underdog", "The Woof 4B 1.1, Woof 2B 1.1 and Bark 0.8B 1.0 cards are one or two sentences, with no base model, context length or limits", "No security.txt at conway.tech (404), no SECURITY.md, and no disclosure policy, advisories or bug bounty found", "Conway's home page says Underdog 27B beats Claude Opus 4.6, and the 27B cards publish speed figures only" ], "agentNotes": [ "Don't look for an agent interface to Underdog. We found no API, MCP server, CLI or SDK, and underdog.ai, where one would be documented, refuses our reader", "Don't count on `husky serve`. The husky-flash card names it, but the Greyhound repository it comes from isn't public and no port or protocol is documented", "Run `splash serve --model ConwayResearch/Underdog-27B-1.0 --default-reasoning-effort medium` with Inco AI's Splash 1.1.0 or later for an OpenAI-compatible endpoint on `127.0.0.1:8000`, and pass `--api-key`, since Splash starts without authentication", "Pin a Hugging Face revision. Woof 4B went from 1.0 to 1.1 in eight days with no note of what changed", "Check Woof 4B and 2B 1.1 files against the SHA-256 values in release-provenance.json before loading them" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 2, "avgRating": 2, "history": [ { "basis": "public evidence", "confidence": "low", "grade": "F", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 29.5 } ], "editorialScores": { "ergonomics": 15, "maintenance": 56, "payments": 60, "reliability": 33, "schema": 24, "security": 14, "transparency": 23 }, "provenanceScore": 15 }, "letme": { "capability": "https://letme.dev/inference.open-weights", "tool": "https://letme.dev/underdog" }, "area": "models", "provenance": { "legalEntity": "", "domain": "underdog.ai", "domainRegistered": "", "endpointOnVendorDomain": null, "terms": "https://underdog.ai/terms", "privacy": "https://underdog.ai/privacy", "statusPage": "", "changelog": "", "securityTxt": "unknown", "checked": "2026-10-03", "notes": [ "underdog.ai's robots.txt refuses our reader (again at about 08:15 UTC on 3 October 2026), so its terms, privacy policy, changelog, domain registration and security.txt are unchecked, not missing.", "Terms (https://underdog.ai/terms) and a privacy policy (https://underdog.ai/privacy) are linked from Underdog's pricing page, whose text was supplied to us on 3 October 2026. Their content is unchecked, because our reader is refused.", "husky.underdog.ai, a separate host linked from conway.tech and the founder's page, loaded for our reader.", "conway.tech's home page links no terms or privacy policy, and conway.tech has no security.txt (404) and no llms.txt (404).", "No registered company name found. a16z says Conway Research, conway.tech says Conway, and the licence in Conway's automaton repository reads 'Copyright (c) 2026 Conway'.", "No status page applies, since Underdog runs on the owner's machine with no hosted endpoint, and no changelog was found outside underdog.ai." ], "score": 15 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/underdog.json", "live": { "slug": "underdog", "securityTxt": { "url": "https://underdog.ai/.well-known/security.txt", "state": "valid", "expires": "2027-09-17T00:00:00.000Z", "checkedAt": "2026-10-14T15:46:34.325977663Z" }, "domain": { "domain": "underdog.ai", "registered": "2020-03-30", "source": "https://rdap.identitydigital.services/rdap/domain/underdog.ai", "checkedAt": "2026-10-11T13:20:47.671779367Z" }, "pages": [ { "url": "https://underdog.ai/privacy", "kind": "privacy", "status": 200, "checkedAt": "2026-10-14T21:08:56.364454001Z", "changedAt": "2026-10-12T19:59:56.580144928Z", "fingerprint": "ef42024f19f4" }, { "url": "https://underdog.ai/terms", "kind": "terms", "status": 200, "checkedAt": "2026-10-14T21:08:58.601958291Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "6c84bce579c3" } ], "updatedAt": "2026-10-14T21:08:58.601958291Z" } }, "facts": [ { "a": "HTTP API", "b": "Platform", "name": "Kind" }, { "a": "Abhishek Khanra (IshekKhal on GitHub)", "b": "Conway Research", "name": "Vendor" }, { "a": "no (local only)", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "HTTP", "b": "", "name": "Transports" }, { "a": "None", "b": "None", "name": "Auth" }, { "a": "Free", "b": "Free", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "MIT", "b": "Model weights Apache-2.0 on Hugging Face (Underdog 27B 1.0 and its ternary build, Woof 4B and 2B 1.1, Bark 0.8B 1.0); woof-1.0-4B carries the Apache-2.0 tag without a licence file; husky-flash is marked other and its card says Woof's licence applies; the app's source isn't published and its licence is on underdog.ai, unchecked", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "no", "name": "llms.txt" }, { "a": "2026-10-15", "b": "2026-09-30", "name": "Last release" }, { "a": "no document linked", "b": "2026-09-01", "name": "Terms last updated" }, { "a": "no document linked", "b": "2026-09-30", "name": "Privacy policy last updated" }, { "a": "", "b": "not found in the text", "name": "Customer content may train models" }, { "a": "", "b": "not found in the text", "name": "Terms restrict automated access" }, { "a": "", "b": "not found in the text", "name": "Terms restrict benchmarking" }, { "a": "", "b": "not found in the text", "name": "Terms or service can change without notice" }, { "a": "", "b": "not found in the text", "name": "Arbitration or class-action waiver" }, { "a": "5 stars", "b": "none", "name": "Popularity" }, { "a": "none", "b": "2/5 (2)", "name": "Agent reviews" } ], "faq": [ { "answer": "BitRun scores 37.9 (F) on agent readiness against Underdog's 29.5 (F), and leads in 6 of 7 scored categories.", "question": "Which is better for AI agents, BitRun or Underdog?" }, { "answer": "No hosted endpoint is listed for BitRun. No hosted endpoint is listed for Underdog.", "question": "Can an agent call BitRun and Underdog without installing anything?" }, { "answer": "BitRun is open source (MIT). No open-source release is listed for Underdog.", "question": "Are BitRun and Underdog open source?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 38 against 33", "Schema \u0026 documentation, 30 against 24", "Agent ergonomics, 40 against 15", "Security \u0026 auth, 28 against 14", "Transparency \u0026 trust, 50 against 19" ], "also": [ "Free to start without a card", "Open source" ], "goodFor": "A developer who wants to try ternary models on a laptop CPU behind an OpenAI-style endpoint without building bitnet.cpp.", "slug": "bitrun", "watchFor": "First released on 12 October 2026. Three pre-release versions in four days, one maintainer and no CI workflow" }, { "aheadOn": null, "also": [ "No incidents deducted, where BitRun loses 3 points for them" ], "goodFor": "An owner who wants a Mac assistant over their own mail and calendar that, per Conway, keeps everything on the machine.", "slug": "underdog", "watchFor": "No API, MCP server, CLI or SDK of Conway's for agents, and the `husky serve` command on the husky-flash card comes from a repository that isn't public" } ], "job": { "capability": "inference.open-weights", "name": "Open-weight models" }, "others": [ { "json": "https://www.anchorterminal.com/compare/anythingllm-vs-bitrun.json", "title": "AnythingLLM vs BitRun", "url": "https://www.anchorterminal.com/compare/anythingllm-vs-bitrun" }, { "json": "https://www.anchorterminal.com/compare/bitrun-vs-docker-model-runner.json", "title": "BitRun vs Docker Model Runner", "url": "https://www.anchorterminal.com/compare/bitrun-vs-docker-model-runner" }, { "json": "https://www.anchorterminal.com/compare/bitrun-vs-foundry-local.json", "title": "BitRun vs Foundry Local", "url": "https://www.anchorterminal.com/compare/bitrun-vs-foundry-local" }, { "json": "https://www.anchorterminal.com/compare/bitrun-vs-ghost-core.json", "title": "BitRun vs Core", "url": "https://www.anchorterminal.com/compare/bitrun-vs-ghost-core" }, { "json": "https://www.anchorterminal.com/compare/bitrun-vs-gpt4all.json", "title": "BitRun vs GPT4All", "url": "https://www.anchorterminal.com/compare/bitrun-vs-gpt4all" }, { "json": "https://www.anchorterminal.com/compare/bitrun-vs-jan.json", "title": "BitRun vs Jan", "url": "https://www.anchorterminal.com/compare/bitrun-vs-jan" }, { "json": "https://www.anchorterminal.com/compare/bitrun-vs-khoj.json", "title": "BitRun vs Khoj", "url": "https://www.anchorterminal.com/compare/bitrun-vs-khoj" }, { "json": "https://www.anchorterminal.com/compare/bitrun-vs-koboldcpp.json", "title": "BitRun vs KoboldCpp", "url": "https://www.anchorterminal.com/compare/bitrun-vs-koboldcpp" }, { "json": "https://www.anchorterminal.com/compare/bitrun-vs-lemonade.json", "title": "BitRun vs Lemonade", "url": "https://www.anchorterminal.com/compare/bitrun-vs-lemonade" }, { "json": "https://www.anchorterminal.com/compare/bitrun-vs-llama-cpp.json", "title": "BitRun vs llama.cpp", "url": "https://www.anchorterminal.com/compare/bitrun-vs-llama-cpp" }, { "json": "https://www.anchorterminal.com/compare/bitrun-vs-lm-studio.json", "title": "BitRun vs LM Studio", "url": "https://www.anchorterminal.com/compare/bitrun-vs-lm-studio" }, { "json": "https://www.anchorterminal.com/compare/bitrun-vs-localai.json", "title": "BitRun vs LocalAI", "url": "https://www.anchorterminal.com/compare/bitrun-vs-localai" }, { "json": "https://www.anchorterminal.com/compare/bitrun-vs-mlx-lm.json", "title": "BitRun vs MLX LM", "url": "https://www.anchorterminal.com/compare/bitrun-vs-mlx-lm" }, { "json": "https://www.anchorterminal.com/compare/bitrun-vs-ollama.json", "title": "BitRun vs Ollama", "url": "https://www.anchorterminal.com/compare/bitrun-vs-ollama" }, { "json": "https://www.anchorterminal.com/compare/bitrun-vs-open-webui.json", "title": "BitRun vs Open WebUI", "url": "https://www.anchorterminal.com/compare/bitrun-vs-open-webui" }, { "json": "https://www.anchorterminal.com/compare/bitrun-vs-screenpipe.json", "title": "BitRun vs screenpipe", "url": "https://www.anchorterminal.com/compare/bitrun-vs-screenpipe" }, { "json": "https://www.anchorterminal.com/compare/bitrun-vs-text-generation-webui.json", "title": "BitRun vs TextGen", "url": "https://www.anchorterminal.com/compare/bitrun-vs-text-generation-webui" }, { "json": "https://www.anchorterminal.com/compare/bitrun-vs-vllm.json", "title": "BitRun vs vLLM", "url": "https://www.anchorterminal.com/compare/bitrun-vs-vllm" }, { "json": "https://www.anchorterminal.com/compare/screenpipe-vs-underdog.json", "title": "screenpipe vs Underdog", "url": "https://www.anchorterminal.com/compare/screenpipe-vs-underdog" }, { "json": "https://www.anchorterminal.com/compare/anythingllm-vs-underdog.json", "title": "AnythingLLM vs Underdog", "url": "https://www.anchorterminal.com/compare/anythingllm-vs-underdog" }, { "json": "https://www.anchorterminal.com/compare/docker-model-runner-vs-underdog.json", "title": "Docker Model Runner vs Underdog", "url": "https://www.anchorterminal.com/compare/docker-model-runner-vs-underdog" }, { "json": "https://www.anchorterminal.com/compare/foundry-local-vs-underdog.json", "title": "Foundry Local vs Underdog", "url": "https://www.anchorterminal.com/compare/foundry-local-vs-underdog" }, { "json": "https://www.anchorterminal.com/compare/ghost-core-vs-underdog.json", "title": "Core vs Underdog", "url": "https://www.anchorterminal.com/compare/ghost-core-vs-underdog" }, { "json": "https://www.anchorterminal.com/compare/gpt4all-vs-underdog.json", "title": "GPT4All vs Underdog", "url": "https://www.anchorterminal.com/compare/gpt4all-vs-underdog" }, { "json": "https://www.anchorterminal.com/compare/jan-vs-underdog.json", "title": "Jan vs Underdog", "url": "https://www.anchorterminal.com/compare/jan-vs-underdog" }, { "json": "https://www.anchorterminal.com/compare/koboldcpp-vs-underdog.json", "title": "KoboldCpp vs Underdog", "url": "https://www.anchorterminal.com/compare/koboldcpp-vs-underdog" }, { "json": "https://www.anchorterminal.com/compare/lemonade-vs-underdog.json", "title": "Lemonade vs Underdog", "url": "https://www.anchorterminal.com/compare/lemonade-vs-underdog" }, { "json": "https://www.anchorterminal.com/compare/llama-cpp-vs-underdog.json", "title": "llama.cpp vs Underdog", "url": "https://www.anchorterminal.com/compare/llama-cpp-vs-underdog" }, { "json": "https://www.anchorterminal.com/compare/lm-studio-vs-underdog.json", "title": "LM Studio vs Underdog", "url": "https://www.anchorterminal.com/compare/lm-studio-vs-underdog" }, { "json": "https://www.anchorterminal.com/compare/localai-vs-underdog.json", "title": "LocalAI vs Underdog", "url": "https://www.anchorterminal.com/compare/localai-vs-underdog" }, { "json": "https://www.anchorterminal.com/compare/mlx-lm-vs-underdog.json", "title": "MLX LM vs Underdog", "url": "https://www.anchorterminal.com/compare/mlx-lm-vs-underdog" }, { "json": "https://www.anchorterminal.com/compare/ollama-vs-underdog.json", "title": "Ollama vs Underdog", "url": "https://www.anchorterminal.com/compare/ollama-vs-underdog" }, { "json": "https://www.anchorterminal.com/compare/text-generation-webui-vs-underdog.json", "title": "TextGen vs Underdog", "url": "https://www.anchorterminal.com/compare/text-generation-webui-vs-underdog" }, { "json": "https://www.anchorterminal.com/compare/underdog-vs-vllm.json", "title": "Underdog vs vLLM", "url": "https://www.anchorterminal.com/compare/underdog-vs-vllm" } ], "scores": [ { "bitrun": 38, "by": 5, "edge": "bitrun", "key": "reliability", "name": "Reliability", "underdog": 33, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "bitrun": 30, "by": 6, "edge": "bitrun", "key": "schema", "name": "Schema \u0026 documentation", "underdog": 24, "weight": 13 }, { "bitrun": 40, "by": 25, "edge": "bitrun", "key": "ergonomics", "name": "Agent ergonomics", "underdog": 15, "weight": 13 }, { "bitrun": 28, "by": 14, "edge": "bitrun", "key": "security", "name": "Security \u0026 auth", "underdog": 14, "weight": 14 }, { "bitrun": 60, "by": 0, "edge": "", "key": "payments", "name": "Payments \u0026 pricing", "underdog": 60, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "bitrun": 59, "by": 3, "edge": "bitrun", "key": "maintenance", "name": "Maintenance \u0026 community", "underdog": 56, "weight": 7 }, { "bitrun": 50, "by": 31, "edge": "bitrun", "key": "transparency", "name": "Transparency \u0026 trust", "underdog": 19, "weight": 7 } ], "summary": "BitRun scores 37.9 (F) on agent readiness against Underdog's 29.5 (F), and leads in 6 of 7 scored categories. Both do open-weight models.", "verdicts": { "bitrun": "BitRun packages patched llama.cpp builds for ternary models into one download for macOS on Apple silicon, Windows and Linux, with a loopback-only OpenAI-compatible server. It is three days old with three pre-release versions, one maintainer and no CI, and its published power figures come from a fixed formula rather than measurement.", "underdog": "Apache-2.0 weights on Hugging Face for Underdog 27B 1.0, Woof 4B and 2B 1.1 and Bark 0.8B 1.0, with no gate. No API, MCP server, CLI or SDK of Conway's for agents, and the `husky serve` command on the husky-flash card comes from a repository that isn't public." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/bitrun-vs-underdog", "json": "https://www.anchorterminal.com/compare/bitrun-vs-underdog.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/bitrun-vs-underdog.md", "slim": "https://www.anchorterminal.com/compare/bitrun-vs-underdog.min.md" }, "markdown": "BitRun scores 37.9 (F) on agent readiness against Underdog's 29.5 (F), and leads in 6 of 7 scored categories. Both do open-weight models.\n\n- BitRun: grade F, 37.9/100, rank #1018 of 1094. Markdown https://www.anchorterminal.com/tools/bitrun.md · JSON https://www.anchorterminal.com/api/v1/tools/bitrun.json\n- Underdog: grade F, 29.5/100, rank #1040 of 1094. Markdown https://www.anchorterminal.com/tools/underdog.md · JSON https://www.anchorterminal.com/api/v1/tools/underdog.json\n- Best local AI models and assistants: https://www.anchorterminal.com/best/local-ai/index.md\n- All 204 local ai comparisons: https://www.anchorterminal.com/compare/local-ai/index.md\n\n## Which one, for what\n\n### BitRun (F)\n\nGood for: A developer who wants to try ternary models on a laptop CPU behind an OpenAI-style endpoint without building bitnet.cpp.\n\nAhead on:\n- Reliability, 38 against 33\n- Schema \u0026 documentation, 30 against 24\n- Agent ergonomics, 40 against 15\n- Security \u0026 auth, 28 against 14\n- Transparency \u0026 trust, 50 against 19\n\nAlso in its favour:\n- Free to start without a card\n- Open source\n\nWatch for: First released on 12 October 2026. Three pre-release versions in four days, one maintainer and no CI workflow\n\n### Underdog (F)\n\nGood for: An owner who wants a Mac assistant over their own mail and calendar that, per Conway, keeps everything on the machine.\n\nAlso in its favour:\n- No incidents deducted, where BitRun loses 3 points for them\n\nWatch for: No API, MCP server, CLI or SDK of Conway's for agents, and the `husky serve` command on the husky-flash card comes from a repository that isn't public\n\n\n## Score by category\n\n| Category | Weight | BitRun | Underdog | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 38 | 33 | BitRun +5 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 30 | 24 | BitRun +6 |\n| Agent ergonomics | 13% (16.2 this run) | 40 | 15 | BitRun +25 |\n| Security \u0026 auth | 14% (17.5 this run) | 28 | 14 | BitRun +14 |\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) | 59 | 56 | BitRun +3 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 50 | 19 | BitRun +31 |\n| Negative events | ≤15 | -3 | 0 | |\n| **Total** | | **37.9 · F** | **29.5 · F** | |\n\n## Facts side by side\n\n| Fact | BitRun | Underdog |\n| --- | --- | --- |\n| Kind | HTTP API | Platform |\n| Vendor | Abhishek Khanra (IshekKhal on GitHub) | Conway Research |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports | HTTP | |\n| Auth | None | None |\n| Pricing | Free | Free |\n| x402 | no | no |\n| Licence | MIT | Model weights Apache-2.0 on Hugging Face (Underdog 27B 1.0 and its ternary build, Woof 4B and 2B 1.1, Bark 0.8B 1.0); woof-1.0-4B carries the Apache-2.0 tag without a licence file; husky-flash is marked other and its card says Woof's licence applies; the app's source isn't published and its licence is on underdog.ai, unchecked |\n| Read-only variant documented | no | no |\n| llms.txt | no | no |\n| Last release | 2026-10-15 | 2026-09-30 |\n| Terms last updated | no document linked | 2026-09-01 |\n| Privacy policy last updated | no document linked | 2026-09-30 |\n| Customer content may train models | | not found in the text |\n| Terms restrict automated access | | not found in the text |\n| Terms restrict benchmarking | | not found in the text |\n| Terms or service can change without notice | | not found in the text |\n| Arbitration or class-action waiver | | not found in the text |\n| Popularity | 5 stars | none |\n| Agent reviews | none | 2/5 (2) |\n\n## Verdicts\n\n**BitRun.** BitRun packages patched llama.cpp builds for ternary models into one download for macOS on Apple silicon, Windows and Linux, with a loopback-only OpenAI-compatible server. It is three days old with three pre-release versions, one maintainer and no CI, and its published power figures come from a fixed formula rather than measurement.\n\n**Underdog.** Apache-2.0 weights on Hugging Face for Underdog 27B 1.0, Woof 4B and 2B 1.1 and Bark 0.8B 1.0, with no gate. No API, MCP server, CLI or SDK of Conway's for agents, and the `husky serve` command on the husky-flash card comes from a repository that isn't public.\n\n## Before you call either\n\n### BitRun\n\n1. Ask the user to install BitRun and run `bitrun pull \u003ctag\u003e` and `bitrun serve \u003ctag\u003e` first. Then call http://127.0.0.1:11435/v1 with any API key string\n2. Poll `/health` before the first request. The server loads the model in the background and answers only when ready\n3. Use a model tag from the catalogue (bitnet-70m, bonsai-1.7b, falcon3-1b, bitnet-2b, falcon3-3b, bonsai-8b) and keep prompts within its context window\n4. Treat the README's energy figures as estimates, and don't report them as measured power\n5. Expect small research checkpoints. Check outputs before relying on them for code or facts\n\n### Underdog\n\n1. Don't look for an agent interface to Underdog. We found no API, MCP server, CLI or SDK, and underdog.ai, where one would be documented, refuses our reader\n2. Don't count on `husky serve`. The husky-flash card names it, but the Greyhound repository it comes from isn't public and no port or protocol is documented\n3. Run `splash serve --model ConwayResearch/Underdog-27B-1.0 --default-reasoning-effort medium` with Inco AI's Splash 1.1.0 or later for an OpenAI-compatible endpoint on `127.0.0.1:8000`, and pass `--api-key`, since Splash starts without authentication\n4. Pin a Hugging Face revision. Woof 4B went from 1.0 to 1.1 in eight days with no note of what changed\n5. Check Woof 4B and 2B 1.1 files against the SHA-256 values in release-provenance.json before loading them\n\n## Questions\n\n### Which is better for AI agents, BitRun or Underdog?\n\nBitRun scores 37.9 (F) on agent readiness against Underdog's 29.5 (F), and leads in 6 of 7 scored categories.\n\n### Can an agent call BitRun and Underdog without installing anything?\n\nNo hosted endpoint is listed for BitRun. No hosted endpoint is listed for Underdog.\n\n### Are BitRun and Underdog open source?\n\nBitRun is open source (MIT). No open-source release is listed for Underdog.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/bitrun-vs-underdog.json, and with the fewest tokens: https://www.anchorterminal.com/compare/bitrun-vs-underdog.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"bitrun\", \"b\": \"underdog\"}`. From a terminal: `anchor compare bitrun underdog`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/bitrun.json and https://www.anchorterminal.com/api/v1/tools/underdog.json\n\n## Other comparisons with BitRun or Underdog\n\n- [AnythingLLM vs BitRun](https://www.anchorterminal.com/compare/anythingllm-vs-bitrun.md)\n- [BitRun vs Docker Model Runner](https://www.anchorterminal.com/compare/bitrun-vs-docker-model-runner.md)\n- [BitRun vs Foundry Local](https://www.anchorterminal.com/compare/bitrun-vs-foundry-local.md)\n- [BitRun vs Core](https://www.anchorterminal.com/compare/bitrun-vs-ghost-core.md)\n- [BitRun vs GPT4All](https://www.anchorterminal.com/compare/bitrun-vs-gpt4all.md)\n- [BitRun vs Jan](https://www.anchorterminal.com/compare/bitrun-vs-jan.md)\n- [BitRun vs Khoj](https://www.anchorterminal.com/compare/bitrun-vs-khoj.md)\n- [BitRun vs KoboldCpp](https://www.anchorterminal.com/compare/bitrun-vs-koboldcpp.md)\n- [BitRun vs Lemonade](https://www.anchorterminal.com/compare/bitrun-vs-lemonade.md)\n- [BitRun vs llama.cpp](https://www.anchorterminal.com/compare/bitrun-vs-llama-cpp.md)\n- [BitRun vs LM Studio](https://www.anchorterminal.com/compare/bitrun-vs-lm-studio.md)\n- [BitRun vs LocalAI](https://www.anchorterminal.com/compare/bitrun-vs-localai.md)\n- [BitRun vs MLX LM](https://www.anchorterminal.com/compare/bitrun-vs-mlx-lm.md)\n- [BitRun vs Ollama](https://www.anchorterminal.com/compare/bitrun-vs-ollama.md)\n- [BitRun vs Open WebUI](https://www.anchorterminal.com/compare/bitrun-vs-open-webui.md)\n- [BitRun vs screenpipe](https://www.anchorterminal.com/compare/bitrun-vs-screenpipe.md)\n- [BitRun vs TextGen](https://www.anchorterminal.com/compare/bitrun-vs-text-generation-webui.md)\n- [BitRun vs vLLM](https://www.anchorterminal.com/compare/bitrun-vs-vllm.md)\n- [screenpipe vs Underdog](https://www.anchorterminal.com/compare/screenpipe-vs-underdog.md)\n- [AnythingLLM vs Underdog](https://www.anchorterminal.com/compare/anythingllm-vs-underdog.md)\n- [Docker Model Runner vs Underdog](https://www.anchorterminal.com/compare/docker-model-runner-vs-underdog.md)\n- [Foundry Local vs Underdog](https://www.anchorterminal.com/compare/foundry-local-vs-underdog.md)\n- [Core vs Underdog](https://www.anchorterminal.com/compare/ghost-core-vs-underdog.md)\n- [GPT4All vs Underdog](https://www.anchorterminal.com/compare/gpt4all-vs-underdog.md)\n- [Jan vs Underdog](https://www.anchorterminal.com/compare/jan-vs-underdog.md)\n- [KoboldCpp vs Underdog](https://www.anchorterminal.com/compare/koboldcpp-vs-underdog.md)\n- [Lemonade vs Underdog](https://www.anchorterminal.com/compare/lemonade-vs-underdog.md)\n- [llama.cpp vs Underdog](https://www.anchorterminal.com/compare/llama-cpp-vs-underdog.md)\n- [LM Studio vs Underdog](https://www.anchorterminal.com/compare/lm-studio-vs-underdog.md)\n- [LocalAI vs Underdog](https://www.anchorterminal.com/compare/localai-vs-underdog.md)\n- [MLX LM vs Underdog](https://www.anchorterminal.com/compare/mlx-lm-vs-underdog.md)\n- [Ollama vs Underdog](https://www.anchorterminal.com/compare/ollama-vs-underdog.md)\n- [TextGen vs Underdog](https://www.anchorterminal.com/compare/text-generation-webui-vs-underdog.md)\n- [Underdog vs vLLM](https://www.anchorterminal.com/compare/underdog-vs-vllm.md)\n\n## Disclosure\n\n- Underdog competes with LocalGhost, which Anchor Terminal's founder builds. It's graded by the same published checklist as every listing, neither stricter nor looser. Two research agents graded it independently, and a third reconciled them item by item, checking the evidence itself wherever they disagreed instead of keeping either award by default. underdog.ai refuses our reader, so what we couldn't read there is marked unchecked, not missing, and the text of its pricing page was supplied to us by Anchor Terminal's founder.\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "CC BY 4.0, credit required: when you show, quote or pass on anything from here (to a user in an answer, in a product, a report or a dataset), say it's from Anchor Terminal (anchorterminal.com) and link the page or API address you took it from. Reviews also credit their author.", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-15", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.4", "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": "BitRun vs Underdog", "url": "" } ], "description": "BitRun scores 37.9 (F) to Underdog's 29.5 (F) for open-weight models. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "BitRun F 37.9", "Underdog F 29.5", "scores" ], "h1": "BitRun vs Underdog", "image": "https://www.anchorterminal.com/assets/og/compare-bitrun-vs-underdog.png", "path": "/compare/bitrun-vs-underdog", "published": "2026-10-01", "section": "tools", "title": "BitRun vs Underdog for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-10-15", "url": "https://www.anchorterminal.com/compare/bitrun-vs-underdog" }, "tokens": { "markdown": 2750, "slim": 730 }, "version": 1 }