Tell LearnBuddy what you want to learn, in one conversation, and it works out where to start, what to do each day, and when yesterday's material needs another look. You describe the goal, whether that is a language, programming, nutrition, writing, or a career change, and three to five adaptive questions measure your actual baseline instead of making you pick a level from a dropdown. From there it builds a personalized path of four to twenty-four weeks and tells you daily what to study and what to review, so opening the app answers the question instead of raising it. Forgetting is treated as a scheduling problem: reviews resurface at spaced intervals, weekly self-checks test whether the plan still fits, and the roadmap replans dynamically when you race ahead or fall behind. Two editions run from the same codebase: try the hosted Cloud experience, or settle into Personal mode with your own model API key and your learning data stored on your own server. Optional OpenClaw and Feishu integration can bring the daily guidance into the chat tools you already live in. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Codex LB Enhanced is a session-aware gateway that pools your ChatGPT accounts so a long Codex session survives quota limits, dropped connections, and paused accounts without losing the conversation. It serves Codex desktop, CLI, and IDE clients through the native Responses protocol and WebSocket transport, and answers any OpenAI-compatible client through the familiar /v1 endpoints. When an account runs out of quota, gets suspended, times out, or drops mid-stream, the gateway classifies the failure, removes that account from the current request, and selects the next one through your load-balancing policy. Verified request history, including interrupted tool-call context, is replayed across the account switch when it is safe, so the client sees a slower answer instead of a dead stream. Every API key carries its own policy: time windows from five hours to monthly, limits by credits, tokens, or cost, and model-specific rules. Usage appears in native Codex quota headers and in a /v1/usage view backed by the same data, so editors and automation agree on what is left. Diagnostics correlate each request with its upstream account, transport, failover stage, and retry count, and a web dashboard manages accounts, keys, usage windows, request logs, and recovery reports. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

With 6,600+ GitHub stars and created by vas3k — one of the indie developer community's most recognized builders — TaxHacker is the self-hosted AI accounting application that turns receipt chaos into structured financial intelligence without surrendering a single document to third-party cloud services. Upload photos of receipts, invoices, or PDF bank statements, and the LLM pipeline automatically extracts dates, merchants, amounts, line items, tax breakdowns, and vendor information into an Excel-like structured database with custom fields you define through your own AI prompts. Currency handling covers 170+ fiat currencies and 14 cryptocurrencies (BTC, ETH, LTC, and more) with automatic conversion using historical exchange rates from the actual transaction date — critical for international freelancers filing in one reporting currency. The AI layer supports OpenAI (GPT-4o, GPT-4.1-mini), Google Gemini, Mistral, or fully local models via Ollama, LM Studio, vLLM, and LocalAI through OpenAI-compatible endpoints for complete air-gapped deployments. Features include multi-project workspace isolation, custom categories with AI-driven auto-classification, bulk document upload with batch processing, email server monitoring for automated attachment ingestion, flexible CSV export with attached documents, and comprehensive tax report generation. The tech stack runs Next.js 15+ for the frontend and tRPC API, Prisma ORM for database models and migrations, PostgreSQL 17+ for persistence, and Ghostscript plus GraphicsMagick for PDF rendering. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Your next favorite record is hiding in your listening history, and Digarr is the self-hosted discovery engine that finds it, scores it, and queues it for your library. Connect ListenBrainz, Last.fm, Spotify, Deezer, Discogs, or your Plex, Jellyfin, Emby, or Subsonic server, and Digarr builds a taste profile from what you actually play. An AI provider you choose, from Anthropic, OpenAI, and Gemini to a local Ollama model, proposes candidates, and a weighted scoring system ranks them by consensus, similarity, genre overlap, and your past feedback. Every suggestion lands in a review queue where you can preview tracks, approve, reject, or permanently block artists before anything touches your collection. Approve an artist and Digarr adds them to Lidarr with your quality profile, queues the release in slskd, or exports a playlist to Spotify, Navidrome, Jellyfin, Emby, or Plex. Album-level discovery runs on its own: Release Radar catches new releases from artists you follow, Library Gap-Fill surfaces the studio albums you are missing, and scheduled subscriptions keep fresh candidates flowing in without you lifting a finger. Share the instance with family or friends, each with their own queue and connections, protected by local accounts or OIDC single sign-on, and get notified through webhooks, ntfy, Telegram, or Apprise when new picks arrive. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

With over 33,000 GitHub stars and a codebase written in 92.9% Rust for maximum performance and memory safety, Tabby is the most widely adopted self-hosted alternative to GitHub Copilot — delivering real-time code completions entirely on your own infrastructure with zero code leaving your network. Deploy a single Docker container on any NVIDIA CUDA, Apple Silicon Metal, AMD ROCm, or CPU-only server and connect VS Code, JetBrains IDEs (IntelliJ, PyCharm, WebStorm, GoLand), Vim, Neovim, and Emacs through native extensions. The completion engine supports a curated registry of models including StarCoder2 (1B to 15B parameters), DeepSeek-Coder, CodeLlama, CodeGemma, Qwen2.5-Coder, and Mistral Code — swappable at runtime through the admin dashboard without redeployment. Repository indexing parses your Git repositories and feeds project-specific types, function signatures, and patterns into completion context via RAG, producing suggestions that understand your codebase rather than generic boilerplate. The Answer Engine provides instant responses to code queries within the IDE, while inline chat enables contextual code editing and explanation without switching windows. The admin dashboard manages per-developer API tokens, usage analytics, and model configuration. Enterprise features include SSO via LDAP, OAuth, and SAML, role-based access control, and audit logging for compliance environments. A single RTX 4090 workstation serves a team of 10-15 developers with sub-500ms completion latency. 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.

Transforming fragmented research notes, daily technical logs, and project documentation into an interconnected knowledge base is what NoteDiscovery delivers for privacy-conscious teams and researchers. Writers compose rich documents using a dual-pane editor that renders MathJax equations, interactive task lists, and dynamic Mermaid sequence diagrams side by side with raw text. The interactive knowledge graph maps semantic relationships across notebooks, allowing researchers to explore backlinks, uncover hidden topical connections, and navigate complex idea webs visually. Team members sketch architecture diagrams and wireframes directly inside note canvases using the integrated drawing tool, saving revisions as embedded image layers without external editors. The platform organizes thoughts through flexible tag hierarchies, nested folder trees, and reusable document templates equipped with automatic date and variable substitutions. Autonomous coding assistants and language models query documentation, create structured meeting summaries, and update project indexes directly through the native Model Context Protocol server. Built-in export tools convert notebook collections into standalone HTML packages, printable documents, or portable Markdown archives for offline archiving. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

SourceWeft is an AI workstation you host yourself, where agents, your documents, and your model keys work in one place instead of scattering across chat tabs you do not control. Describe a job and a lead agent breaks it down, handing research, exploration, and execution to focused sub-agents that share the same working context and files. Agents draw on a skill library covering presentations, HTML pages, images, meeting summaries, and study guides, and you can add your own skills so good workflows become repeatable. MCP servers, web search, and web extraction connect agents to outside tools, while approved commands run inside a sandboxed environment that cannot touch the rest of your server. Feed it PDFs, web pages, notes, YouTube videos, Notion, Drive, Gmail, or Slack, then follow citations from any answer back to the source material it came from. Bring your own keys for the chat and indexing models you prefer, organize the team into workspaces with roles and access controls, and pick up any conversation from the web app or desktop clients. 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.

Thousands of frames land on the card after a wedding shoot, and Facet finds the keepers among the bursts, blinks, and near-duplicates. Facet scores every photo across nine dimensions, aesthetic quality, composition, face quality, eye sharpness, technical sharpness, color, exposure, subject saliency, and dynamic range, with category-specific weights for portraits, landscapes, wildlife, and 30-plus other content types. The culling darkroom groups bursts and visually similar frames, protects exposure brackets and panorama sequences, and flags closed eyes per face, so you keep the sharpest open-eyed frame and reject the rest in one pass. Face detection clusters into people you can rename, merge, and search, while albums, star ratings, favorites, and AI content tags organize what survives. Browse survivors through a mosaic gallery with semantic search by plain description, a timeline, a geotag map, and slideshow capsules. Statistics dashboards track your gear usage and metric correlations, and the weight editor learns from A/B comparisons so scores drift toward your own taste. Shared album links support client proofing with hearts and comments, phones auto-upload over the built-in WebDAV inbox, and ratings round-trip to Lightroom, darktable, and Immich through XMP sidecars. Everything runs locally on your own hardware: no cloud accounts, no subscriptions, no photo ever leaves the server. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Stop hoping your AI coding assistant remembers to plan before it codes, test after it implements, and review before it ships. Archon wraps Claude Code, OpenAI Codex, and other AI agents inside structured YAML workflows that enforce the same development process every single time. Define your pipeline as a directed acyclic graph of nodes (AI tasks, shell scripts, approval gates, loops) and Archon handles the orchestration: resolving dependencies, running independent nodes in parallel, passing artifacts between steps, and isolating every run in its own git worktree so five bug fixes can proceed simultaneously without conflicts. Ship with 17 pre-built workflows covering everything from "idea to merged PR" to automated conflict resolution, or author your own by committing YAML files to your repository's .archon/workflows/ directory. The web dashboard, launched with archon serve, provides a conversation interface with real-time streaming, a visual drag-and-drop workflow builder for creating DAG pipelines, step-by-step progress monitoring for every run, and a unified sidebar aggregating conversations from CLI, Slack, Telegram, and GitHub into one view. An NLP router parses natural language requests and automatically selects the right workflow. Structured JSON output schemas let you enforce typed responses from AI nodes, with validation and auto-repair for providers that lack native schema support. Every workflow file is version-controlled, portable, and reviewable in pull requests, so your entire team runs identical processes from day one. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

DevTrack turns your GitHub activity into a living dashboard of commit streaks, pull-request analytics, and goals that quietly update themselves. Sign in with GitHub and your last year appears as a contribution heatmap you can filter by repository and language, next to the streak you are protecting and the freeze you are saving for a holiday. Pull requests get the honest treatment: merge rate, average review time, and open-versus-closed breakdowns that show whether reviews or authors are the bottleneck. Weekly and monthly goals fill themselves in from live activity, while the consistency score and activity rings tell you whether your rhythm is steady or heroic but rare. When you want the story told back to you, an AI mentor who knows your history offers guidance, a résumé generator builds an ATS-friendly CV from merged pull requests for the role you name, and a weekly summary explains your own graphs in plain words. Opt into the public leaderboard to rank your streak, commits, and PRs against other developers, or keep everything private and share only the profile page and embeddable badges you choose. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Strength training, cardio, and body metrics land in one workout log on your own server, backed by an optional AI coach that explains its advice from your real numbers. Quick entry such as 100x8@9 logs weight, reps, and effort in one line, with a rest timer, plate-loading calculator, and warm-up ramp beside the set table. A weight picker offers only loads your equipment can build, and a readiness check-in adjusts the suggested load and says why. Templates for 5/3/1 BBB, GZCLP, nSuns, PPL, and Upper/Lower run as written and edit like any custom program. Progress pages chart estimated 1RM, weekly volume per muscle group against MEV and MRV bands, a muscle heat map, bodyweight goals, and a training calendar. Garmin FIT, TCX, and GPX imports need no cloud account and add heart-rate charts and aerobic decoupling to each run or ride. The coach writes a weekly debrief, chats in a streaming conversation, and drafts a full program from a one-sentence goal, using your own Anthropic or OpenRouter key. History imports from Strong or Hevy CSV files with a dry-run preview and exports to CSV or TCX, and an MCP connector lets ChatGPT or other agents analyse it. The app installs as an offline-capable PWA, speaks English, French, Russian, and German, and keeps every user's data separate. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Upload a report, ask a "what if" question in plain language, and MiroFish builds a small simulated society that plays out the answer before you commit to a decision. It reads your seed documents, whether news, policy drafts, financial signals, or a novel, and extracts entities and relationships into a GraphRAG knowledge graph. Entities from the graph become agents with a profession, a biography, and interest tags, and the app estimates simulation rounds from the simulated time span, with a custom mode for shorter runs. Agents post and react on two simulated platforms at once, a feed-style plaza and a topic community, while a live monitor tracks rounds, elapsed simulated time, and actions. A ReportAgent then plans an outline and writes the prediction report section by section with the InsightForge, PanoramaSearch, QuickSearch, and InterviewSubAgent tools. Afterward you can keep questioning the ReportAgent, chat with any individual agent, or send a survey question to a selected group and read their answers. Typical uses include rehearsing public relations responses, testing policy drafts against likely reactions, and exploring alternate endings for a story. The interface switches between English and Chinese, and you bring your own model: any OpenAI SDK compatible LLM endpoint works, Zep Cloud stores agent memory, and the project suggests starting under 40 rounds because runs consume many tokens. 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.

WebCodex gives ChatGPT, Claude, and other MCP clients a real development environment on machines you own, so an AI assistant can edit your actual repositories instead of a pasted snapshot. A self-hosted Server authenticates every request and routes it to a Runner sitting next to your code, where file edits, Git operations, test runs, shell commands, and long jobs execute with your real toolchain. Your projects never move into a hosted workspace; only the tool results you authorize travel back to the model. The browser Runtime Console shows project readiness, the work queue, session activity, and connected Runners, and it is where you decide pending approvals or accept and reject finished work, because the model cannot approve its own changes. Runners join with a short-lived pairing code and stay connected over QUIC, WebSocket, or polling, so machines behind NAT still work. One-command sharing opens a temporary session for a single repository, while durable setups run the Server and Runner as system services behind your own HTTPS domain. Workflow Sessions keep evidence and context across conversations, so long tasks survive closed browser tabs and threads you pick up days later. 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.

Transform complex code repositories into searchable, interactive wikis with DeepWiki, an automated documentation platform that maps architectural relationships and provides instant answers to technical questions about any codebase. Software engineers can submit public or private repositories from GitHub, GitLab, or Bitbucket to generate comprehensive project overviews, component breakdowns, and interactive Mermaid diagrams illustrating data pipelines and class hierarchies. The built-in Ask interface allows developers to query system logic using retrieval-augmented answers grounded directly in repository source files. Teams can trigger iterative deep research sessions that perform multi-step codebase investigations to explain intricate execution paths, uncover hidden dependencies, and summarize complex algorithms across hundreds of files. Interactive Codemap tours provide guided walkthroughs of critical entry points, letting reviewers inspect synchronized code viewer panels with exact line references while onboarding to unfamiliar services. Developers can export complete wiki structures for offline sharing, customize documentation depth from high-level summaries to granular module analyses, and connect local or cloud model endpoints to process sensitive internal code securely. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

One endpoint, every model you run, and a government-grade paper trail for each request. OpenGateLLM sits in front of your AI infrastructure as the single door: applications call one OpenAI-compatible API, and the gateway decides which backend answers, a self-hosted vLLM cluster, an Ollama box in the corner, a Hugging Face TEI embeddings service, or a hosted provider when you allow one. You publish friendly model names as routers and attach real provider APIs behind them, then load-balance across those backends by shuffle or least-busy so a second GPU node starts earning its keep the moment you register it. Chat completions, embeddings, reranking, OCR, and audio transcription each get their standard endpoint, so existing OpenAI SDK code, LangChain, and LlamaIndex projects point at a new base URL and keep working. Governance is built in rather than bolted on: organizations, users, and roles control who may call which model, API keys authenticate every request, and rate limiting keeps one enthusiastic team from eating the whole cluster. Usage monitoring follows every inference, and carbon footprint estimates attach to models through their hosting zone and parameter counts. Retrieval-augmented generation against Elasticsearch or Qdrant plugs into the same surface. No chat history is stored, which is rather the point when the data is yours. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Agent code needs somewhere disposable to run, and Sandstorm turns one modest VPS into a fleet of thousands of isolated sandboxes that wake the moment work arrives. You create sandboxes through a plain HTTP API, starting from a registered template or forking a tagged snapshot, with per-sandbox memory ceilings, attached volumes, and egress rules set on each call. Every sandbox is a gVisor container with its own network namespace, so untrusted agent code runs away from your host and away from its neighbors. Idle sandboxes cool down through four tiers, from running hot, to frozen in place with a wake time near ten milliseconds, to checkpointed on disk and back in about a fifth of a second, so a small machine can hold far more sandboxes than it could ever keep running at once. A single binary acts as master, node, and web console: the master tracks desired state and places work across nodes, nodes behind NAT dial out to join the fleet, and a gateway on each node wakes a sleeping sandbox and forwards its traffic automatically. The built-in Hub pulls ready-made snapshot packs for warmed runtimes like Python with numpy or a pre-warmed Playwright browser, skipping cold starts entirely. 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.

Bifrost is an open-source AI gateway that unifies 23+ LLM providers into a single OpenAI-compatible endpoint with automatic failover, semantic caching, and built-in cost governance, so one provider going down never takes your production AI application with it. Point your existing OpenAI or Anthropic SDK at Bifrost's local endpoint and gain access to OpenAI, Anthropic, AWS Bedrock, Google Vertex, Azure, Groq, Mistral, and Ollama without changing application code. Define fallback chains that automatically switch providers when one returns errors or exceeds latency thresholds, keeping response times stable during outages. The built-in web dashboard at port 8080 lets you configure providers, create virtual API keys, monitor live request traffic, and review analytics without editing configuration files. Semantic caching combines exact hash matching with vector similarity search via Weaviate, serving cached responses for identical or paraphrased prompts in sub-millisecond time to cut costs on repetitive workloads. The MCP gateway connects AI agents to external tools like filesystems, databases, and web APIs, exposing them to clients such as Claude Desktop and Cursor with per-key allow-lists. Four-tier budget hierarchy at customer, team, virtual key, and provider levels enforces spend caps, rate limits, and model restrictions across your organization. Extend functionality through custom Go plugins for analytics, monitoring, or security middleware. Native Prometheus metrics and OpenTelemetry distributed tracing give operations teams full production observability. 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.

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.