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.

Your prompts never have to leave the building: TextGen runs open large language models on your own hardware behind a chat interface and an API that speak fluent OpenAI. Load GGUF or Hugging Face weights through llama.cpp, ik_llama.cpp, Transformers, ExLlamaV3, or TensorRT-LLM, and switch models or backends from the interface without restarting the server. Chat mode gives you conversations with characters and system prompts, notebook mode behaves like a familiar completion editor, and both accept image attachments for vision models and documents for context. Models that support tool calling can search the web, fetch pages, and do math through single-file Python tools, and MCP servers plug in for larger tool catalogs. Start it with the API flag and the same model answers at chat, completions, and messages endpoints that mirror OpenAI and Anthropic, complete with streaming, logprobs, embeddings, and optional API key authentication. Portable builds for Linux, Windows, and macOS bundle every dependency, so the distance from download to a running model is an unzip and one shell command. Because everything is local, prompts, documents, and outputs stay on machines you control, and parallel request handling lets a single loaded model serve a whole team's tools at once. 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.

With over 15,900 GitHub stars and 40,000 weekly npm downloads in its first two months, OpenWiki from LangChain has rapidly become the standard for AI-generated codebase documentation. Built on the Deep Agents framework, it deploys a documentation agent that reads your repository's source code, tests, and configuration, then synthesizes a complete linked Markdown wiki with architecture overviews, integration guides, data-flow diagrams, and validated Mermaid visualizations. Two operating modes cover distinct workflows: code mode generates repository documentation in an openwiki/ folder with automatic AGENTS.md and CLAUDE.md integration for Codex, Claude Code, OpenCode, and Cursor, while personal mode builds a local knowledge base from nine connectors including Notion, Slack, Gmail, X/Twitter, Hacker News, LangSmith, Custom MCP, Web Search, and local git repositories. Thirteen model providers are supported out of the box — OpenAI, Anthropic, Gemini, AWS Bedrock, GitHub Copilot, OpenRouter, Nebius, Fireworks, Baseten, NVIDIA NIM, and any OpenAI-compatible endpoint like Ollama or LM Studio. Grounded Claims track every material assertion back to versioned source evidence, flagging stale propositions before they propagate. The interactive visualizer renders wiki pages as an explorable node graph with a side-by-side Markdown reader, exportable as a static site for GitHub Pages or MkDocs. Self-updating CI workflows via GitHub Actions, GitLab CI, or Bitbucket Pipelines open documentation PRs automatically when code changes. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Instead of burying your documents in a vector index you cannot inspect, LLM Wiki v2 files them into a Markdown wiki you can read, browse, and question. Drop text, Markdown, or PDF files anywhere on the page and each one is catalogued automatically, filed into a folder that says what it holds, and linked to the notes it relates to. Ask a question and the answer cites the exact notes it used, with clickable sources you can open, verify, and correct. New documents update the note on their subject instead of piling up as disconnected chunks, so what you teach it stays taught. A small classifier routes filing and questions through the folder tree, keeping the wiki quick and cheap as it grows, and you can browse the tree, follow see-also links, move or delete notes, and watch the tokens spent by both the model and the classifier. Connect OpenRouter, OpenAI, Gemini, a local Ollama, or any compatible endpoint, and expose the same wiki to Claude Code or Codex as long-term memory they can recall from and write to. Because every note is plain Markdown in a folder you own, the whole knowledge base can live in git beside your other files. 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.

DB-GPT lets a team talk to its data: ask a business question in plain English, and an AI agent plans the work, writes the SQL, runs it, and hands back charts and a written report. Connect MySQL, PostgreSQL, SQL Server, ClickHouse, DuckDB, Doris, StarRocks, or MaxCompute, or drop in CSV and Excel files, including several at once. Every step appears in a live task view with its query, result table, code, and console output, and the agent pauses to ask clarifying questions, with answer options, when the data cannot settle the matter. Reusable skills package proven procedures, including CSV analysis, SQL analysis, and financial report analysis, and a skill creator helps write new ones. Code executes in a sandbox, parallel sub-agents split larger jobs, and an agentic knowledge-base search answers questions over uploaded documents. Scheduled tasks run saved conversations on a cron timetable with on/off switches and execution history, while MCP connectors link tools like Notion, Linear, Tavily, and GitHub. Pick OpenAI, DeepSeek, Qwen, SiliconFlow, Ollama, or vLLM for the model, then use the application and AWEL workflow tools to build data apps of your own. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

big-AGI is an open-source generative AI workspace that provides a unified, local-first interface for orchestrating multi-model reasoning, automated code execution, and custom persona workflows across private infrastructure. Users query multiple large language models simultaneously through the Beam scatter-gather engine, which prompts independent AI systems in parallel, compares candidate completions side by side, and merges optimal passages into a single refined response. Knowledge workers assemble tailored AI personas equipped with specialized system instructions, custom temperature settings, and predefined document context to handle domain-specific tasks ranging from architectural design reviews to legal contract analysis. The application renders rich multimedia outputs including interactive Mermaid sequence diagrams, LaTeX mathematical formulas, syntax-highlighted code blocks with live execution previews, and AI-generated image generation canvases. Teams integrate local inference servers like Ollama and LocalAI alongside commercial API endpoints to route confidential datasets strictly through internal networks while monitoring per-prompt token usage and operational latency. Users attach complex PDF documents, spreadsheets, and source code repositories for automatic parsing and semantic retrieval, while local-first storage engines ensure private chat transcripts and custom presets remain encrypted on host drives. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Before a language model learns from your data, someone has to label it well; Argilla gives AI engineers and domain experts a shared workspace to label, review, and refine the datasets that fine-tune language models and train NLP pipelines. You build each dataset from the Python SDK, mixing text, chat, and image fields with the exact questions your task needs: single-label classification for intent detection, span questions for named entities, ratings for response quality, rankings for preference tuning, or free text for corrections. Annotators then work through records in a focused labeling interface where model predictions already sit attached as suggestions, turning most reviews into a fast confirm-or-correct decision instead of a blank-page exercise. Full-text search, metadata filters, and status filters slice a hundred thousand records down to the ones needing attention, while vector-based semantic search finds lookalike examples, near-duplicates, and the disagreement hotspots where guidelines need sharpening. Dataset owners watch completion progress, manage who has responded to what, and split work across workspaces with owner, admin, and annotator roles for each team or client. Finished datasets export with responses, suggestions, and metadata intact, locally or straight to the Hugging Face Hub, ready for fine-tuning and evaluation runs. 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.

OpenLLM serves any large language model as an OpenAI-compatible API endpoint from a single CLI command, handling model download, backend selection, quantization, and port binding automatically. It supports the full spectrum of popular models including Llama 3.3, Qwen2.5, DeepSeek, Mistral, and Phi3, choosing between vLLM and PyTorch inference backends based on hardware capabilities. When vLLM is available, continuous batching with PagedAttention achieves up to 23x throughput improvement over naive serving, while GPTQ and bitsandbytes quantization reduces memory requirements for GPU-constrained deployments. The server exposes a RESTful API on port 3000 with full OpenAI client library compatibility, enabling drop-in replacement for commercial providers in any application using the standard chat completions format. A built-in web chat UI at the /chat endpoint provides immediate interactive testing without external clients. Custom model repositories allow teams to maintain private catalogs of fine-tuned models alongside the default repository that tracks the latest releases. Deployment workflows generate production-ready Docker images automatically, with Kubernetes manifest support for orchestrated scaling. Native integration with LangChain and LlamaIndex supports RAG pipelines, Transformers Agents enables tool-calling workflows, and HuggingFace Hub handles model discovery. Server-Sent Events enable real-time token streaming across all API endpoints. Backed by BentoML's production ML infrastructure. 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.

Proval is a self-hosted AI code review agent that reads every pull request on your GitLab, Forgejo, or GitHub server and posts a consolidated, severity-grouped review with inline comments, using a model you run yourself. When a pull request gets a meaningful push, a planning agent groups changed files into review units and dispatches specialist sub-agents in parallel, each exploring the codebase so cross-file issues surface. A writing agent merges their findings into one review, with comments on the affected lines, including multi-line ranges. Reply to any Proval comment and it reads the thread context and answers, and it works on issues too, greeting new ones and answering follow-ups on every message or only when mentioned. Choose per repository whether reviews run on first push only, every push, or not at all, skipping drafts until they are marked ready. Every review, reply, and issue comment is logged with its token usage, so each model's cost shows in the dashboard instead of hiding in an API bill. Your code is never stored; review context goes only to the LLM endpoint you configure, whether that is a cloud API or a local Ollama or llama.cpp server on your own network. Connect GitLab or Forgejo with an access token and webhooks, or GitHub through a GitHub App; Gitea and Codeberg use the same Forgejo-compatible path. 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.

Retrieval-augmented chatbots on your own knowledge base - that is the whole mission of Dialoqbase, an open-source bot-building platform. Feed it content through a broad set of data loaders - web pages and full crawls, sitemaps, PDFs, DOCX, CSV, plain text, GitHub repositories, YouTube videos, and MP3/MP4 audio - and it handles the whole RAG pipeline in one self-contained app: chunking, embedding, vector storage, and LLM querying. The distinguishing architecture choice is PostgreSQL with pgvector for embedding storage and similarity search, which removes the separate vector-database dependency, and Redis-backed Bull queues for ingesting large documents without blocking the API. Model choice is wide open: OpenAI, Anthropic Claude, Google Gemini, Cohere, Fireworks, Hugging Face, local models via Ollama, and any OpenAI-compatible endpoint, with an equally broad list of embedding providers. Finished bots embed on any website with customizable styling or deploy to Telegram, Discord, and WhatsApp, and an API creates and manages bots programmatically. Multi-user support adds registration limits and per-user bot quotas. MIT-licensed and free for commercial use.

Sage Wiki turns a pile of unstructured documents into a fully interlinked, searchable wiki by running them through a five-pass LLM compiler pipeline. Inspired by Andrej Karpathy's vision of LLM-compiled knowledge bases, the pipeline processes source files through diff detection, summarization, concept extraction, image captioning, and cross-reference discovery, with parallel LLM calls and checkpoint/resume for vaults scaling to 100,000+ documents. The typed ontology graph stores entities and relations with BFS traversal, configurable relation types, multilingual synonyms, and a promotion/demotion lifecycle backed by grounding verification and consensus scoring. Multi-format ingestion handles Markdown, PDF, Word, Excel, PowerPoint, EPUB, email, CSV, images, and code files without manual tagging. LLM provider support spans Anthropic, OpenAI, Gemini, Ollama, and any OpenAI-compatible API, with per-pass model routing enabling cost optimization by assigning cheaper models to simpler tasks. The built-in MCP server exposes 17 tools over SSE transport for integration with Claude, Cursor, and any MCP-compatible agent, while native Obsidian vault overlay ensures existing note workflows remain undisrupted. Team deployment supports Git-synced shared wikis, centralized server access, and hub federation across multiple projects. Ships as a single Go binary with Docker Compose multi-arch images serving the web UI on port 3333. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

BitRouter is a context-aware LLM router that learns which model delivers the cheapest successful outcome per workflow step, cutting agent costs by up to 80% while maintaining 96% quality versus all-frontier baselines. Point any agent runtime at http://localhost:4356 with a one-line OPENAI_BASE_URL change and BitRouter routes to OpenAI, Anthropic, Google, Groq, DeepSeek, Mistral, Moonshot, MiniMax, Nvidia, and any OpenAI-compatible endpoint simultaneously, normalizing authentication, streaming, and cross-protocol translation between wire formats. The act-observe-evaluate-learn loop traces every hop with cost, tokens, and latency attribution, scores each decision against a versioned policy-lock.yaml, then tightens routes automatically with no LLM judge in the path. Native MCP gateway auto-discovers tools from connected servers and makes them routable and governed alongside model calls. Agent Client Protocol integration enables the TUI to manage Claude Code, Codex, OpenCode, OpenClaw, Gemini, and Copilot sessions in real time with inline tool-call approval and live streaming. Built-in guardrails inspect, redact, or block risky content before requests leave your network. Virtual keys scope API access per agent or user without exposing upstream credentials. Per-agent spend caps and loop guards contain runaway cost automatically. Multi-account failover reroutes mid-run so rate limits never re-pay completed work. Ships as a single Rust binary via npm or Cargo. 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.

Bring your own API keys and work with OpenAI GPT models, Anthropic Claude, Google Gemini, Mistral, DeepSeek, Grok, Azure endpoints, and local models in one organized workspace: TypingMind is a unified chat frontend for large language models, replacing a browser tab per provider. Parallel chat sends the same prompt to multiple models and compares answers side by side, and models can be switched mid-conversation. A prompt library stores reusable, tagged prompts with variables, and the AI Agents system builds specialized assistants that bundle a base model, custom instructions, assigned plugins, and uploaded knowledge files for RAG. Plugins extend every connected model with web search, image generation (DALL-E, Stable Diffusion), Deep Research, URL reading via Firecrawl, and Zapier automation - plus MCP server integrations for Notion, Atlassian, and other external tools, and a JavaScript extension API for custom behavior. Chats store locally by default with optional sync. Self-hosting puts the interface on your own domain and, for teams, adds branding, member access limits, and shared prompt and agent libraries.

One clean interface in front of Anthropic, OpenAI, Google Gemini, Cohere, and more: Chat Chat is a Next.js front door to the major AI providers, ending the juggling of separate subscriptions, tabs, and UIs per model. Bring your own API keys, pick a provider and model per conversation, and switch between them as the task demands: Claude for long-form reasoning, GPT for code, Gemini for multimodal work - the interface stays identical. Beyond configured presets, custom providers plug in with their own API endpoints and keys, which covers OpenAI-compatible gateways and local inference servers. The design splits into two dedicated modes: a chat interface for conversational work with customizable system prompts, and a search interface that pairs AI processing with query handling for research-style questions. The stack is modern and hackable - Next.js 14, Tailwind CSS, shadcn/ui on Radix primitives, Jotai for state - with full internationalization including English, Chinese, and Japanese. Self-hosting means your conversation history and API keys live on your instance rather than a third-party wrapper service, and pay-per-token API pricing typically beats stacking multiple monthly chat subscriptions. AGPL-licensed and deliberately simple to deploy: one container, environment variables for keys, done.

Why should your chat history live on someone else's servers? Chatpad AI - a React/TypeScript front end for the OpenAI API, built on the Mantine component library - is designed around that question. Enter your own OpenAI API key and start chatting with GPT models; every conversation, prompt, and setting is stored locally in your browser via DexieJS over IndexedDB, with no tracking, no cookies, and no backend database at all. That architecture is the point - the Docker image is just Nginx serving static files, making it one of the lightest AI deployments in the catalog, and pay-per-token API pricing typically undercuts a ChatGPT Plus subscription for moderate use. The interface earns its "premium quality" tagline with the details: a persona selector that switches communication styles per conversation, a saved-prompts library for messages you reuse constantly, organized chat history, and full data export/import so conversations move between browsers or into backups as files you control. A JSON config file customizes defaults - models, API endpoints, UI options - without rebuilding the image. AGPL-licensed, with desktop builds available upstream. For teams that want ChatGPT's utility with a self-hosted, zero-telemetry footprint, Chatpad is the minimal, sane answer.

Whirl puts every top AI model in a single conversation and remembers what you were working on last week, so you can switch models mid-thought without losing the thread. Ask for a report, a chart, or a small interactive page and it appears as a living artifact in a side panel, still editable while you keep chatting, and shareable by link when it is ready to leave the conversation. Connect your own tools over MCP, with OAuth sign-in handled for you, or install skills that teach the app new tricks your team relies on. Long-term memory carries your preferences and project context from chat to chat, and live web search with page reading grounds answers in today's pages instead of the model's training data. Sensitive threads can be locked with a password that encrypts them on your device, where the server never sees the key and only zero-retention models may answer. Around those headline pieces sits the everyday kit: incognito mode, a message queue for when you think faster than the model replies, voice input, image generation, file attachments, folders, and sharing controls. An admin console manages the model catalog, integrations, and skills, and the interface itself switches between light and dark with your choice of accent color, installable as a mobile web app. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

DispatchMail is an SuperHuman alternative and delivers a self-hosted AI email assistant that processes your Gmail inbox through configurable OpenAI prompts without sending data to third-party cloud services beyond the LLM API itself. The Flask backend connects to Gmail via IMAP, retrieves new messages according to your schedule, and routes them through customizable whitelist rules based on sender address, subject keywords, or natural language descriptions before AI processing begins. Two distinct prompt configurations control behavior — the Reading Prompt instructs how the AI should analyze and classify incoming messages, while the Draft Prompt defines how responses should be composed, letting you maintain consistent tone and policy across all automated replies. Whitelist filtering ensures the AI only processes messages you explicitly authorize, preventing unnecessary API costs and keeping sensitive emails out of the LLM pipeline entirely. The React web interface provides inbox management with message previews, AI-generated summaries, draft editing with human-in-the-loop approval before sending, and configuration panels for prompts and rules. Automatic labeling and archival organize processed messages into categories without manual intervention. The sender research feature uses LLM-powered deep analysis to build background profiles of email contacts. All email content, credentials, and processing results persist in a local SQLite database with zero cloud storage dependencies. 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.

SmarterRouter stops you from playing model roulette with your local AI setup, choosing the right model for every prompt so you never have to. Point your applications at one familiar endpoint and send the request; the router studies the prompt, weighs category and complexity against benchmark results gathered on your actual hardware, and hands the job to the model most likely to answer well. It discovers the models your backend already serves, profiles each one with standard tests the first time it meets them, and keeps learning from the feedback your usage generates. When the first choice fails, a backup model takes over without your application noticing. Repeated questions come straight back from cache instead of burning another generation. Your graphics memory is watched continuously across one card or several, and models are unloaded before an ambitious request runs the machine dry. Cloud providers can join the same routing pool when a question deserves them, while everything local stays local and free. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.