Speakr transforms audio recordings into organized, searchable, AI-enhanced notes with speaker recognition that identifies who said what across your entire recording library. The Python/Flask backend with Vue.js 3 and Tailwind CSS frontend deploys via Docker on port 8899, offering multiple transcription engines through auto-detected connectors: WhisperX for local processing with speaker diarization and voice embeddings, OpenAI Whisper and GPT-4o-transcribe, Mistral Voxtral for cloud diarization, AssemblyAI for multi-hour files, and any custom ASR webservice. Speaker voice profiles use embedding comparison to recognize individuals across different recordings automatically, while custom vocabulary biases the transcriber toward domain-specific jargon. The AI layer goes well beyond transcription: customizable summaries with per-recording, per-tag, and per-folder prompt templates; event extraction surfacing action items and calendar events; per-recording chat with streaming responses; and Inquire Mode for semantic search and natural-language queries across your entire library simultaneously. Smart tags execute custom AI prompts on transcripts for automatic categorization. The REST API with Swagger documentation supports signed webhooks integrating with n8n, Zapier, and Make. Auto-export pushes to Obsidian and Logseq, auto-processing watches directories, and the installable PWA provides mobile-first, offline-capable access with share-target support. 3,600+ stars since May 2025. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. AGPL-3.0 licensed.

Originated as Alibaba Group's official internal AI code review assistant serving tens of thousands of developers and identifying millions of code defects over two years before open-sourcing in May 2026 — now at 21,000+ GitHub stars — Open Code Review is the production-hardened platform that proves enterprise-grade code review can be fully open-source under Apache 2.0. The hybrid architecture separates deterministic engineering pipelines (file selection, diff parsing, rule matching for NPE, thread-safety, XSS, and SQL injection across 10+ languages) from LLM-powered agent reasoning with tool-use capabilities including FileRead, CodeSearch, and cross-file context inspection, consuming approximately one-ninth the tokens of general-purpose coding agents while delivering line-level precise comments with severity and confidence scoring. The bundled web dashboard (port 4173) provides review management, findings triage, result browsing, and direct GitHub posting without external dependencies, while the session viewer (port 5483) renders full LLM request/response traces for debugging and auditing. Integration spans GitHub Actions, GitLab CI, GitFlic CI, and Gerrit with delegation mode enabling Claude Code, Cursor, and other AI agents to leverage OCR's engineering logic alongside their own LLM reasoning. Supports OpenAI, Anthropic, Google Gemini, DeepSeek via built-in providers plus Ollama and vLLM for air-gapped deployments. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache 2.0 licensed.

The fastest tool on the public Martian Code Review Bench at 77 seconds per PR with competitive F1 scores — while every higher-scoring competitor takes 5 to 14 times longer — Mira is the fully open-source AI code reviewer that ships the entire feature surface other tools gate behind per-seat subscriptions: indexed PR reviews with full-repo context, streaming walkthroughs posted within seconds, inline vulnerability scanning from hourly OSV.dev polls, org-wide package inventory answering "which repos use [email protected]?" in one query, interactive dependency graphs with blast-radius SVG rendering via ReactFlow, a learning loop that synthesizes rules from rejected comments and human review patterns on merged PRs, and cost telemetry showing actual spend per repo and per model. Unlike CodeRabbit, Greptile, and GitHub Copilot code review which are SaaS-only with per-seat pricing, Mira runs as a single Docker image on your infrastructure with your LLM key through OpenRouter (fronting Anthropic, OpenAI, Google Gemini, DeepSeek) or direct to Ollama and vLLM for fully air-gapped deployments. The engine indexes Python, TypeScript, Go, Rust, Java, C/C++, C#, Swift, Kotlin, Scala, and PHP with per-file symbol extraction, enabling multi-file reasoning across diffs rather than isolated line-by-line review. Integrates with GitHub, GitLab, and Forgejo via webhook with full feature parity. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache 2.0 licensed.

Before a change lands in the main branch, Review Board gives your team a self-hosted code review server where reviewers read the diff, open issues on specific lines, and sign off with a Ship It. Post a review request from the web or with RBTools, either before you commit or after, and every update becomes a new revision that stays in the history. Interdiffs show exactly what changed between revisions, and moved-code detection keeps rearranged blocks from drowning out real edits. Comments can open issues that reviewers later mark fixed or dropped. Images and Markdown files can be reviewed alongside code, with split, onion-skin, color, and side-by-side diffs for pictures. A dashboard with customizable columns separates incoming from outgoing requests by review group. Connect Git, Mercurial, Subversion, or Perforce repositories, including ones hosted on GitHub or GitLab, and review them all on one server. Slack and Discord notifications, Jenkins builds, and Review Bot linters report back inside the review. Private repositories and hidden or invite-only review groups restrict who sees what, with sign-in through Active Directory, LDAP, or SAML 2.0. A REST API, WebHooks, and Python extensions cover custom workflows. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

ScribeCrate is a self-hosted speech-to-text API that turns recordings into transcripts, subtitles, and English translations on your own server. It speaks the OpenAI Whisper API fluently: point any compatible client at your server's address, swap in your API key, and uploads come back as text. Ask for plain text, JSON with timestamps, or ready-to-publish SRT and WebVTT subtitle files, and for long recordings the segments can stream back over SSE as they are decoded. Turn on speaker diarization and every segment is labeled with who is speaking, which makes interview and meeting transcripts readable at a glance. Choose the model that fits the job, from tiny for quick drafts to large-v3 for maximum accuracy, and run it on a modest CPU, a Raspberry Pi class ARM board, or an NVIDIA GPU. Almost any recording works: MP3, M4A, WAV, WebM, OGG, and FLAC are all accepted, and with models cached in advance the server keeps transcribing with no internet connection at all. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

From a PDF plan set to a waste-adjusted material order takes one browser tab: OpenTakeoff measures floors, walls, and fixtures at the drawn scale and never uploads a single drawing. Drag in a PDF, image, or zip plan set, view up to four sheets side by side, and search sheet text, while stitching joins floors split across a match line. Scale comes from the drawn scale note or a known dimension, and a check tool reports percent error before a wrong scale can skew a bid. Area, linear, and count tools carry condition colors, CAD hatches, waste percentages, and wall heights, and a marquee over the architect's finish schedule turns approved rows into conditions. Supporting materials convert coverage rates into rounded-up order quantities, and roll-goods mode lays out lanes, seams, and cuts to scale. Totals in SF, SY, LF, and EA export to CSV, JSON, Excel, print, or a marked-set PDF, while named revisions compare addenda as quantity deltas. Highlighters, revision clouds, callouts, and notes mark up sheets on a layer that is never counted, and dimension lines label measured lengths at the sheet scale. An MCP server with more than 50 tools lets AI agents open plans, set scale, and measure rooms, and each shape they draw stays a dashed proposal until a person accepts it. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. AGPL-3.0 licensed.

Subarr is the coordination, measurement, and quality layer for Whisper subtitle generation, sitting between Bazarr, Sonarr, Radarr, and subgen to decide what gets transcribed, in what order, and whether the result is any good. Its Coverage walk scans your whole library and scores every subtitle gap with a reason: no track, embedded-only, Bazarr-wanted, audio mislabeled, or low quality. Queue a file, a folder, or an entire series from the Library tab and watch it move through probing, transcribing, and write-back on the dashboard. The Review queue plays you the actual dialogue, picked out by voice-activity detection, so you can verify a subtitle really matches the audio language before it lands. It flags files whose default audio track is not the original language and swaps tracks in place, heading off the double-translation trap. A provider leaderboard records which subtitle sources actually deliver for your library, and the Tuning Lab lets you tune Whisper recipes against your own media. Rules and scheduled walks keep the work flowing, with Tautulli now-playing signals boosting whatever you are about to watch. Finished subtitles are written next to your media, and your Plex or Jellyfin library refreshes the moment one lands. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Audio lectures become structured, Markdown-formatted notes in about a minute with ScribeWizard (also known as GroqNotes). Upload an MP3, WAV, or M4A file - or paste a YouTube link - and the app runs a three-stage pipeline on Groq's LPU inference hardware: Whisper Large v3 transcribes the audio, a larger Llama model drafts a comprehensive outline of the material, and a faster Llama model fills each section with detailed content. This scaffolded prompting strategy is the core idea: the strong model handles structure where quality matters most, the fast model handles volume, and Groq's 1200+ tokens-per-second inference keeps the whole process near real time. Output renders as clean Markdown with support for tables and code blocks, and finished notes download as text or PDF. Model selection is configurable - swap in other Groq-hosted open models like Mixtral or Gemma to trade speed against quality or work around rate limits. Built as a single Streamlit app by Benjamin Klieger at Groq, it needs only a Groq API key to run, making it one of the simplest self-hosted AI tools to operate.