Reaching #1 on GitHub Trending with over 48,000 stars, OpenMontage is the first open-source agentic video production system — transforming AI coding assistants like Claude Code, Cursor, Copilot, Windsurf, and Codex into complete video studios that handle research, scripting, scene planning, asset generation, editing, and final rendering through natural language prompts. Twelve production pipelines cover animated explainers, cinematic trailers, documentary montages, talking heads, screen demos, podcast repurposing, character animation, localization and dubbing, avatar spokesperson videos, hybrid productions, clip factory batch processing, and animation workflows. Over 100 registered Python tools connect to 60+ providers including Kling, Runway Gen-4, Google Veo 3.1, FLUX, Google Imagen 4, ElevenLabs, and Suno AI for cloud generation, plus Piper TTS, WAN 2.1, Hunyuan, and CogVideo for fully local GPU rendering — while free footage from Archive.org, NASA, Wikimedia Commons, Pexels, and Unsplash powers the documentary montage pipeline's CLIP-indexed retrieval system for real-motion video without paid generation APIs. Two composition engines — Remotion for React-based programmatic video and HyperFrames for HTML/GSAP motion graphics — render final output with spring animations, word-level captions, kinetic typography, and SVG character rigs. A seven-dimension scored provider selector, pre-compose validation gates, post-render ffprobe self-review, slideshow risk scoring, configurable budget caps with per-action approval thresholds, and the Backlot live web dashboard for visual production monitoring enforce production-grade quality at every stage. 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.

The first open-source substrate for enterprise knowledge engineering that learns passively and governs itself. The Rust-built backend paired with PostgreSQL and pgvector delivers a bitemporal knowledge graph where every fact carries two timelines: when it held in the real world and when the system came to believe it — enabling full audit trail replay of how understanding evolved. Document ingestion handles PDF, DOCX, PPTX, XLSX, CSV, Markdown, HTML, and plain text with legacy encoding detection, while scheduled syncing pulls from web pages, RSS feeds, GitHub, Jira, Notion, WebDAV, and S3-compatible buckets. Search fuses Tantivy full-text indexing with pgvector semantic vectors using Reciprocal Rank Fusion, streaming answers with inline citations that link directly to source passages. The built-in agent harness drives agentic RAG through conversation — searching documents, walking the knowledge graph at any historical date, and querying mounted databases via Ontology2SQL which achieves state-of-the-art results on BIRD Mini-Dev benchmarks. Five ontology packs ship inside the binary (schema.org, W3C Org, PROV-O, FOAF, IOF Core) with forward-chaining reasoning for transitivity, symmetry, inverses, and relation hierarchy. Entity resolution operates in three stages: exact name matching, embedding similarity, then model-based judgment with every merge reversible. Any OpenAI-compatible endpoint works including DeepSeek, Qwen, Ollama, and vLLM for fully air-gapped deployment. 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.

With over 330 GitHub stars and described as "OpenRouter, but for agent tools instead of models," Treg is the unified tool registry that gives your AI agent one base URL, one token, and instant access to approximately 2,800 cataloged endpoints across 56 providers — SEO and backlink analysis via Semrush and Moz, social media intelligence from TikTok and Instagram, people and company enrichment through Crunchbase and Hunter, media buying, scraping, and SERP data — all priced per call from fractions of a cent with no provider signup required. The FastAPI backend with PostgreSQL stores credential bindings and injects them server-side into every proxied request, ensuring API keys and OAuth tokens never touch the agent or local machine while every call is audit-logged. Teams register their own paid API accounts, OAuth connections, vendor CLIs like Stripe, GitHub CLI, Vercel, and gcloud, plus custom SKILL.md definitions — all callable by every teammate's agent through a single treg token with automatic credential injection. The evidence-based tool selector shows success rate, response speed, and last-seen timestamp for each provider, so agents pick tools on measured performance rather than guesswork. Bring-your-own-key routes bypass metering entirely, and the one-dollar free credit on every new team lets agents start calling immediately. The Vue.js web dashboard provides team management, audit logs, catalog browsing, and guided onboarding. Self-host with pip install tools-registry[server] 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.

OmniRoute is an AI gateway, aggregating 338 LLM providers including OpenAI, Anthropic Claude, Google Gemini, DeepSeek, Kimi, MiniMax, and GLM into a single OpenAI-compatible endpoint at localhost:20128. The gateway catalogs over 1,200 models across 90 free-tier providers and 40 free-forever providers, automatically rotating through tier-1, tier-2, and tier-3 fallback chains when any provider exhausts its quota or returns errors. RTK plus Caveman stacked token compression reduces eligible context by 15 to 95 percent before forwarding requests, cutting API costs dramatically without degrading output quality. OmniRoute exposes its full routing engine through a built-in MCP server with 104 tools across 31 scopes over stdio, HTTP, and SSE transports, plus an A2A protocol server with six autonomous agent skills and JSON-RPC 2.0 streaming. The gateway integrates directly with Claude Code, Cursor, GitHub Copilot, Codex CLI, OpenCode, and Cline through standard base-URL configuration. Seventeen routing strategies include latency-optimized, cost-minimized, and auto-scoring modes that evaluate candidates on success rate, context fit, model fitness, quota state, and circuit-breaker health. The Next.js dashboard provides real-time provider status, usage analytics, combo chain configuration, and model catalog browsing via a responsive PWA. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Over 2,500 open-source projects and companies in more than 165 countries localize with Weblate - the libre continuous localization platform and the standard self-hosted answer to Crowdin and Lokalise. Its defining trait is that translations live in the same version control as your code: Weblate talks directly to Git and Mercurial, pulls new source strings automatically via webhooks, and pushes finished translations back either as direct commits or as pull/merge requests on GitHub, GitLab, Gitea, Bitbucket, Azure DevOps, Gerrit, or Pagure. Every translator is properly credited in the commit history. For translators, it is a full computer-aided translation tool: translation memory, glossaries, customizable quality checks that catch placeholder and formatting mistakes, propagation of identical strings across components, and automatic suggestions from machine translation services - DeepL, Amazon Translate, LibreTranslate, and others, with per-service priorities and support for custom Python engines. It handles the format zoo (gettext PO, JSON, YAML, Android XML, iOS strings, and dozens more) and supports crowdsourced workflows with granular access control, workspaces, two-factor authentication, and reviewer approval steps. A REST API, CLI client, and add-on system automate everything else. Built on Python/Django, GPL-licensed, with no per-string or per-seat pricing when self-hosted.

TencentDB Agent Memory provides a team-level memory hub that transforms AI agent conversations, documents, and codebases into four governed, shareable memory assets: Chat Memory for conversation history, Skills extracted from completed tasks, LLM-Wiki built from document ingestion, and Code-Graph generated from codebase analysis. The four-tier semantic pyramid structures long-term memory from L0 raw conversation capture through L1 episodic extraction and L2 scenario aggregation to L3 persona synthesis, enabling hierarchical drill-down via node and result references instead of flat vector recall. The Node.js Gateway sidecar handles capture, extraction, storage, recall, and pipeline scheduling through RESTful HTTP v2 endpoints on port 8420, while the Memory Proxy intercepts Anthropic-format API calls to inject team memory context into Claude Code, CodeBuddy, and other coding agents transparently. Local SQLite with the sqlite-vec extension provides the default storage backend with hybrid BM25 keyword plus vector embedding plus reciprocal rank fusion retrieval requiring zero external API dependencies. Teams manage ownership, versions, status, visibility, usage counts, and agent bindings through the Memory Hub dashboard with role-based access control separating System Admin and team-level Admin and Member permissions. Official TypeScript and Python SDKs provide programmatic access for custom framework integration beyond the built-in OpenClaw plugin and Hermes Agent adapter. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

A PostgreSQL database becomes a production-grade GraphQL API the moment Hasura GraphQL Engine points at it: track tables and relationships - existing schemas included - and full query, mutation, and subscription types appear with where, order_by, limit, offset, and on_conflict arguments, no resolvers or boilerplate written. Its Haskell core compiles GraphQL to efficient SQL, and any query becomes a real-time live query with a single keyword, powering dashboards and collaborative UIs over standard GraphQL subscriptions. Authorization is where Hasura earns its enterprise reputation: role-based access control with row- and column-level permission policies driven by session variables from JWTs, auth webhooks, or headers - each role effectively sees its own GraphQL schema containing only what it may touch, integrating cleanly with Auth0, Firebase, or homegrown auth. Event triggers fire webhooks on inserts, updates, and deletes for asynchronous business logic; Actions extend the schema with custom REST handlers; remote schema stitching merges external GraphQL services into one endpoint; and auto-generated REST endpoints serve clients that skip GraphQL. A browser console handles data modeling and API exploration, the CLI manages migrations and metadata as code, and deployment is a single stateless Docker container beside Postgres.

When an AI agent goes wrong at step seven of twelve, Opik, an open-source LLM observability platform, shows the exact trace, tool call, and prompt behind it, then scores your fix against test datasets. Full trace trees capture every LLM call, retrieval step, and tool execution, and you can annotate traces and spans with feedback scores in the UI or through the SDK. Native integrations for OpenAI, Anthropic, LangChain, LlamaIndex, CrewAI, Google ADK, and DSPy, plus OpenTelemetry for any language with an OpenTelemetry SDK, feed traces in, or add the @track decorator to your own functions. Datasets and experiments compare prompt and model versions, scored by LLM-as-a-judge metrics for hallucination, moderation, and RAG relevance, with a PyTest integration to run evaluations in CI. A Prompt Playground tests prompts across models, and the Agent Optimizer SDK helps improve prompts and agents. Production dashboards track feedback scores, trace counts, and token usage, online evaluation rules score live traces, and optional guardrails add safety checks. An MCP server lets Claude Code, Cursor, VS Code Copilot, Codex, or opencode read traces and run evaluations from chat. Run it yourself with the ./opik.sh script on Docker Compose, or a Helm chart on Kubernetes, so trace data stays in your 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.

With over 16,800 GitHub stars and growing rapidly, Maxun has become the go-to open-source platform for teams who need structured web data without writing scrapers. The TypeScript-based platform provides a no-code visual recorder that captures point-and-click interactions in real-time browser sync, automatically generating reusable extraction robots that handle pagination, infinite scrolling, and dynamic content. LLM-powered extraction accepts natural language prompts like "Extract 10 companies from the Y Combinator website" without requiring a URL — Maxun identifies the source and performs the extraction autonomously. The platform handles authentication-protected pages, adapts automatically to website layout changes through self-healing selectors, and exports directly to Google Sheets, Airtable, or any destination via webhooks. Robots run on configurable schedules with cron-based timing, turning any website into a perpetually fresh RESTful API endpoint. The crawl engine discovers and processes linked pages across entire domains with configurable depth and URL filtering, while the search capability runs automated queries across multiple engines. Official Node.js and Python SDKs provide programmatic control over robot creation, execution, and data retrieval, with MCP integration enabling direct connection to AI tools like Claude. The n8n community node enables workflow automation without custom code. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. AGPLv3 licensed.

Agent Zero equips large language models with a persistent virtual Linux desktop, letting autonomous AI agents write code, research the web, and execute multistep tasks without supervision. Operating within an isolated container, the system opens an interactive XFCE graphical desktop in your browser canvas where the agent interacts with GUI applications like Blender and terminal sessions directly. Its embedded browser features interactive annotation tools, letting you click web elements to inspect stylesheet hierarchies, extract component markup, or submit automated testing instructions. You can cowork on spreadsheets, presentations, and Markdown specifications in real time alongside the agent, preserving document revisions through snapshot time travel. A multi-tier memory architecture backed by FAISS vector indexing and SearXNG web discovery retains problem-solving context across projects, while hierarchical delegation spins up specialized subordinate agents to parallelize complex engineering audits. The platform connects seamlessly to commercial LLMs via OpenAI, Anthropic, or OpenRouter, runs private local models through Ollama, and integrates custom toolkits via the Model Context Protocol and community Plugin Hub. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Achieving 98.4% Recall@5 on LongMemEval-S without a reranker, AKB is the agent-native knowledge infrastructure giving Claude Code, Cursor, Windsurf, and any MCP-aware agent persistent organizational memory — a drop-in replacement for Confluence or Notion where AI agents read and write directly rather than scraping human-formatted pages. Documents are stored as Markdown with YAML frontmatter in Git bare repositories (full version history, branching, diff), while PostgreSQL 16 serves as source of truth for chunk text, metadata, and BM25 vocabulary, with dense embeddings handled by a pluggable vector store (pgvector default, Qdrant optional, or managed Seahorse). Agents interact through 20+ MCP tools — akb_put, akb_search, akb_browse, akb_relations, akb_sql, akb_edit, akb_history — performing hybrid dense plus BM25 search fused via Reciprocal Rank Fusion in one call. The URI graph (depends_on, related_to, implements relations) lets agents traverse knowledge connections without external graph databases. Multi-tenant vault isolation is enforced at the PostgreSQL ACL level with per-user roles and SET LOCAL ROLE for SQL sandboxing. Event fanout streams structured events to Redis Streams for external consumers (synthesis bots, digest agents, audit trails), and a hash-chained append-only audit log integrates with enterprise SIEMs. Ships with agent plugins for Claude Code and Codex (session capture, wiki ingest, lifecycle hooks), Kubernetes kustomize manifests, and Open Knowledge Format export. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. BSL 1.1 licensed (free under 100 seats, auto-converts to Apache 2.0 after four years).

Your apps keep using the OpenAI SDK while Antirion, a self-hosted AI gateway, decides which provider answers, what each team may spend, and what gets logged. Clients speak the OpenAI, Anthropic, Gemini, or Bedrock APIs, and Antirion translates between them, so a Claude deployment can answer an OpenAI-style call, streams included. Add providers such as Amazon Bedrock, Vertex AI, Mistral, Groq, DeepSeek, or a vLLM server, then publish them as named Models. Routing rules send traffic by team or project with fallback chains, weighted splits, least-cost or least-latency targets, retries, hedging, and circuit breakers. Budgets and rate limits in dollars or tokens apply per organization, team, project, and key, with projections and alerts before money runs out. Guardrails check for personal data, secrets, keywords, and regex matches, then block, redact, flag, or divert. Exact and semantic caching answers repeated prompts without calling a provider. The request log records every attempt, route, token count, cost, and guardrail verdict, with Prometheus metrics and OTLP traces. An MCP gateway and A2A proxy put tools and agents behind the same keys. Sign in with OIDC, SAML, or GitHub, provision users with SCIM, and review every change in the audit log. Changes you choose can require a change request or a second person's approval, and the Playground sends requests from the console. 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.

An agent run can finish without errors and still give the wrong answer, so TraceRoot traces every model and tool call, flags the production runs that missed the mark, and helps your coding agent ship verified fixes. Each run becomes a browsable call tree with inputs, outputs, latency, and cost, searchable by session or filter. Instrument with the Python or TypeScript SDK, the agent-native CLI, or any OpenTelemetry exporter, with ready integrations for LangChain, LangGraph, OpenAI Agents SDK, CrewAI, Vercel AI SDK, Mastra, and Pydantic AI. Detectors use LLM judges to score live traffic against the behavior you define and can post alerts to Slack. Judge outputs cluster into signals, then a background coding agent reads the traces and your connected GitHub code in a sandbox and recommends changes down to the commit, file, and line. Datasets, test cases, and scored eval runs compare versions so regressions surface before a release, and dashboards of widgets chart your trace data. The CLI hands your coding agent, such as Claude Code or Codex, the traces, signals, detectors, and evals to work from. Self-hosting keeps all of that trace data on infrastructure you control. 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 (core edition).

A man-in-the-middle proxy you run on purpose, mitmproxy lets developers and testers inspect, edit, and replay HTTP and HTTPS traffic from any client. Point a browser, phone, or script at it and every HTTP/1, HTTP/2, HTTP/3, WebSocket, and TLS-protected connection appears as a flow you can open, search, and filter. Content views turn payloads from HTML to Protobuf into readable text. Intercept a request or response before it moves on, change its headers, body, or status by hand, then release it, or save the flow and replay it to the client or the server later. Map local and map remote rules answer requests with files or other URLs, while blocklists, anticache, sticky cookies, and proxy authentication cover routine test chores. Choose the interface that fits the job: a keyboard-driven terminal console, mitmweb in the browser with a Capture tab that sets up WireGuard devices with a QR code, or mitmdump for unattended logging in scripts. Proxy modes include regular, local capture, WireGuard, transparent, reverse, upstream, SOCKS5, and DNS. Addons written in Python add custom rewriting, recording, and automation. Teams use it for debugging, testing, privacy measurements, and penetration testing. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Nearly two decades running engineering organizations: Redmine is the veteran open-source project management and issue tracker, a Ruby on Rails application (GPLv2) still in active development. Its core strength is configurability: define your own trackers (bug, feature, task, or anything else), issue statuses, and role-based workflows that control exactly which transitions each role may perform, then extend records with custom fields of every type. Issues support subtasks, relations (blocks, precedes, duplicates), watchers, categories, and full journaled history, with saved custom queries and cross-project filtering for slicing the backlog any way you need. Around the tracker sit Gantt charts and calendars, a roadmap driven by versions, per-project wikis, forums, news, and document repositories, plus time tracking with estimated versus spent hours and activity-based reporting. Multi-project support runs deep - subprojects, per-project modules, and granular role-based permissions - and repository integration (Git, Subversion, Mercurial) links commits to issues automatically. Email notifications, inbound email-to-issue creation, LDAP authentication, a REST API, and a large plugin and theme ecosystem round it out. Recent 6.x releases brought substantial query and rendering optimizations. Self-hosting keeps your entire project history in your own database, free of per-seat licensing.

One endpoint for every MCP server you run: MCPHub gathers local and remote Model Context Protocol servers behind stable URLs, so AI clients connect once and see what you allow. Claude Code, Cursor, and Cherry Studio can use four routes: everything at /mcp, a named group at /mcp/{group}, one server at /mcp/{server}, or semantic tool search at /mcp/$smart. Smart routing runs vector search on PostgreSQL with pgvector and an OpenAI-compatible key, so the model gets a shorter tool list. Servers attach over stdio, SSE, or streamable HTTP, OpenAPI services can be wrapped as MCP tools, and changes apply without downtime. In the other direction, MCP tools can be exported as an OpenAPI 3.0.3 spec for OpenWebUI and other OpenAPI clients. Bearer keys, OAuth 2.0 (client and server modes), and GitHub or Google sign-in in database mode control access, with per-user visibility for servers and groups. Encrypted per-user credentials let one shared server use each person's own key. Logs show tool-call activity, request status, and latency, health checks track each connection, and the dashboard controls which tools, prompts, and resources each server exposes. Large text tool results can be compressed, interactive MCP Apps are proxied through MCPHub routes, and a built-in market lets you browse a server catalog. Typical uses include a team-wide gateway, per-project groups, and direct single-server routes for debugging. 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.

Describe a component in natural language and watch it render: OpenUI, from Weights & Biases, is an open alternative to Vercel's v0. Type a prompt like "a dark-themed dashboard with a sidebar and charts" and the LLM renders working HTML with Tailwind styling live in the browser. You then iterate conversationally, asking for changes until the design is right, and convert the result to React, Svelte, or Web Components for use in a real project. The backend is Python with LiteLLM routing, so it works with OpenAI, Anthropic, Gemini, Groq, and Mistral API keys, or fully offline against local Ollama models, including vision models like LLaVA that can generate UI from screenshot input - feed a screenshot and the model reproduces or riffs on an existing interface. Generated markup is inspectable at any point, with light and dark mode toggles, theme selection, and responsive previews across device sizes. The practical effect is compressing the mockup-review-revise loop from hours to minutes: a described layout renders in seconds and iterates through follow-up prompts, and because output converts to real framework code, prototypes feed directly into production codebases instead of staying trapped in a design tool. Self-hosting keeps unreleased product interfaces and prompts on your own server, and LiteLLM routing lets you pick the model per task - a cheap fast model for rough drafts, a stronger one for final passes, or free local models for unlimited experimentation.

MateClaw delivers a multi-agent AI platform where digital employees run as persistent team members with roles, goals, and accumulated skills rather than stateless chat completions. The Spring Boot backend on Spring AI Alibaba provides ReAct iterative reasoning and Plan-and-Execute decomposition on a StateGraph runtime, with parallel delegation between employees and dynamic context pruning for multi-step tasks. Five career templates ship ready (Product Researcher, Customer Support, Knowledge Curator, Data Analyst, Executive Assistant) while custom employees inherit configurable backstories, pixel-art avatars, and dedicated tool bindings. The MCP integration supports stdio, SSE, and Streamable HTTP transports with per-employee tool isolation preventing capability bleed between agents. ACP bridges bring Claude Code, Codex, and other coding agents in as first-class employees. Workflow orchestration composes multiple employees and system actions into publishable linear DSL processes with seven step modes: sequential, fan_out, collect, conditional, await_approval, dispatch_channel, and write_memory. The trigger system wires cron schedules, webhooks, channel messages, employee lifecycle events, content matches, and workflow completions to automated flows. The Admin Runtime Console provides real-time visibility into running employees with token usage tracking and one-click force-recycle. Spring Boot Actuator monitoring, full audit trail, and per-channel error isolation deliver production-grade reliability. 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.