Marimo is a reactive Python notebook that treats cells like spreadsheet formulas: change one cell or interact with a UI widget and every dependent cell automatically re-executes, eliminating the hidden state bugs that make traditional notebooks unreliable. Backed by over 22,000 GitHub stars, notebooks are stored as pure Python files with PEP 723 inline metadata, making them Git-diffable, importable as modules, executable as CLI scripts with parameterized arguments, and testable with PyTest. Built-in SQL cells query Polars, Pandas, PyArrow, DuckDB, SQLite, PostgreSQL, and MySQL databases, with results automatically flowing into the reactive dependency graph. The AI-native editor provides GitHub Copilot autocomplete, context-aware assistants that access live runtime variables, inline code edits powered by configurable models from OpenAI, Anthropic, or local Ollama instances, and a pair mode that lets external AI agents connect over WebSocket. Notebooks become read-only interactive web applications with marimo run, collaborative authoring environments with marimo edit, or embedded flows inside existing FastAPI applications through ASGI middleware. Gallery mode serves multiple notebooks from a single instance with an auto-generated index page. The Docker image ships with SQL support, token-based authentication, health check endpoints at /health and /api/status, and configurable WebSocket or SSE kernel transport for proxy compatibility. 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.

To pull a team's skills, MCP servers, hooks, prompts, and agent files out of scattered Git repositories, Observal keeps them in one reviewed registry and traces real sessions to show which ones help. Build an agent visually, with a live config preview for every harness. Submissions wait in an admin review queue, where reviewers inspect side-by-side version diffs before approving a release. Teamspaces give each team its own namespace, and approved releases can be forked into independent drafts. One pull command then writes the right config for Claude Code, Cursor, Kiro, Codex, Copilot, Pi, OpenCode, Antigravity, or Goose. Every approved resource is discoverable through the open Agentic Resource Discovery standard, and a running agent can hand part of its task to another approved agent or a remote Agent2Agent service. Hooks record each session as a trace of prompts, tool calls, MCP round trips, tokens, and errors, with turn-by-turn replay for debugging and audits. Insight reports, generated through providers such as Anthropic, OpenAI, or Ollama, list what is working, what is hindering, and quick wins. A dashboard follows adoption, cost, and department usage, a leaderboard ranks agents by downloads, and audit logs, SAML single sign-on, and SCIM provisioning are included. 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.

Every team building with coding agents has the same drawer problem: the best Skill, MCP server, or agent file lives in one person's repo, undocumented, while three colleagues rebuild it from scratch. Agentic Resource Registry is the internal catalog that ends the duplication, a self-hosted registry where your organization publishes Skills, MCP servers, hooks, prompts, agent files, and sandboxes in one searchable place. Browse by teamspace, publisher, category, or harness and see at a glance what each resource supports and how often it has been pulled. Authors build agent files in a four-step builder with a live summary and draft readiness checks, then submit them into a review queue where admins inspect the full prompt and version diffs before approving. Forking an approved release creates your own draft with pinned components, and reviewers can compare it against upstream line by line. The companion CLI installs any approved resource into Claude Code, Cursor, Codex, Kiro, Copilot, OpenCode, Pi, and more, generating the correct config for each harness automatically. Approved resources are also discoverable over the open ARD standard, so a running agent can hand part of its task to another approved agent or a remote A2A service. 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.

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.

Forge intercepts failing LLM tool calls and fixes them before they derail your agent workflow, applying rescue parsing, retry nudges, response validation, and step enforcement between your AI clients and local model backends. The proxy server mode drops in as a transparent intermediary speaking both the OpenAI chat-completions API and the Anthropic Messages API, so tools like Aider, Claude Code, Continue, and opencode connect through it without configuration changes. Under the hood, the WorkflowRunner provides a complete agentic loop manager with system prompt injection, tool execution, context compaction with configurable thresholds, and VRAM budgeting for consumer GPUs with 12-32 GB. SlotWorker enables priority-queued access to shared inference slots with automatic preemption for multi-agent architectures. The guardrails middleware exposes a two-method check-and-record API that wraps into any existing orchestration loop, providing malformed tool-call rescue parsing, retry nudge generation, required step enforcement, and prerequisite ordering without taking over execution control. Backend adapters support generic OpenAI-compatible endpoints, Ollama, llama-server, Llamafile, vLLM, and Anthropic with automatic model discovery and health checking. Architecture Decision Records document every design choice. Launched February 2026, already at 2,200+ GitHub stars. MIT licensed.

Omni is an open-source workplace AI agent and enterprise search platform that unites your company's scattered tools into a single context-aware workspace where team members can find answers and automate cross-application workflows. Employees can query connected knowledge sources including Google Drive, Gmail, Slack, Jira, GitHub, Confluence, and HubSpot to locate project specifications, customer records, and operational documents without jumping across tabs. The integrated AI assistant answers complex multi-step inquiries, summarizes lengthy email threads, and cites exact source passages so workers can verify factual accuracy before making business decisions. Granular permission inheritance mirrors existing access controls across every connected service, guaranteeing that sensitive personnel files, financial statements, and confidential repositories remain hidden from unauthorized staff. Engineers can construct bespoke data connectors and define automated agent skills through the extensible Python and TypeScript software development kits, triggering multi-service actions directly from interactive chat dialogues. Administrators can monitor background synchronization jobs, inspect audit trails, manage single sign-on access, and configure custom extraction pipelines using centralized operational dashboards. 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.

pgAdmin 4 is the reference administration GUI for PostgreSQL, bundled by virtually every Linux distribution and supporting versions 14 through 18 including EDB Advanced Server — browse schemas in a hierarchical tree, write and optimize queries with AI assistance, design entity-relationship diagrams visually, monitor live sessions, and run backup/restore operations entirely from the browser. Built on Python Flask with a ReactJS frontend, version 9.17 delivers a comprehensive web-based platform accessible from any device. The Query Tool provides syntax highlighting, auto-completion, query history, an EXPLAIN plan visualizer with graphical node representation, AI-powered SQL generation from natural language prompts, and AI Insights for execution plan analysis that identifies performance bottlenecks. The Graph Visualiser renders query results as line charts, bar charts, stacked charts, and pie charts directly in the interface. The ERD Tool auto-generates entity-relationship diagrams from existing schemas for visual database design. The Schema Browser presents databases, schemas, tables, views, functions, sequences, roles, and extensions in a navigable hierarchy. Server monitoring dashboards display real-time active sessions, locks, transaction throughput, and vacuum status. GUI-driven backup and restore wraps pg_dump and pg_restore with format and compression options. Authentication supports internal, LDAP, Kerberos, OAuth2/OIDC, and webserver modes. The Helm chart includes an HTTPRoute template for Kubernetes Gateway API deployments. Bundled pg_dump, pg_restore, and psql utilities version 18.4. Deploy via Docker with the official dpage/pgadmin4 image. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. PostgreSQL License.

API keys hardcoded in repos, database passwords pasted into CI variables, .env files emailed between developers - Infisical, the open-source platform for secrets, certificates, and privileged access management, is the answer to all three. Secrets live in versioned stores scoped by project, environment, and path, with fine-grained identity-aware access control and full audit logging on every read and change. Delivery covers every consumption pattern: CLI injection into local dev, SDKs for Go, Node.js, and Python, an HTTP API, agents, a Kubernetes Operator, and secret syncs that push to GitHub, GitLab, AWS Secrets Manager, and Vercel. Automatic rotation replaces credentials for PostgreSQL, MySQL, MSSQL, LDAP, AWS IAM, and Azure on a rolling schedule - new credentials issue while old ones stay temporarily valid, so nothing breaks mid-rotation. Dynamic secrets go further, generating ephemeral, time-bound database credentials on demand, and SSH access replaces static keys with short-lived CA-signed certificates that expire automatically. Secrets scanning catches hardcoded credentials in code and pipelines, certificate management automates X.509 issuance and renewal, and a built-in KMS handles encrypt/decrypt with central key control. Self-hosting keeps the keys to everything else on your own infrastructure.

Authentication that lives inside your application rather than behind a redirect to an external identity provider - SuperTokens takes a fundamentally different architecture from Auth0 and AWS Cognito. Three tiers make that work - frontend SDKs (React, Angular, Vue, vanilla JS, React Native) render overridable login UI and manage tokens; backend SDKs (Node.js, Python, Go) expose auth endpoints on your own API domain; and SuperTokens Core, the piece you host here, is the stateless HTTP service handling core auth logic, password hashing, token signing, and database operations against PostgreSQL. The recipe system keeps features decoupled: use email/password, social login, passwordless (magic links, OTP), phone-password, multi-factor authentication (TOTP, WebAuthn), user roles, and microservice auth - individually or combined; you can even use SuperTokens purely for session management alongside another login provider. Sessions are where it shines: rotating refresh tokens with theft detection, automatic access-token refresh, CSRF protection, and secure cookie handling out of the box - the details that become vulnerabilities when hand-rolled. Verification happens locally in your backend via cached JWT signing keys, so the Core stays off the hot path. Self-hosted means no user limits, free forever, with all user data in your database. Apache-licensed.

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.

T3 Code puts every coding agent you already pay for behind one control surface, so Claude Code, Codex, Cursor, Grok Build, OpenCode, and Antigravity all run on your server while you direct them from your phone, browser, or desktop. Start a thread, choose the provider and model that fit the job, and watch the agent work in a shared conversation instead of a terminal you have to babysit. Permission modes decide when an agent must stop and ask, and its approvals, questions, and plan reviews arrive in the same thread wherever you happen to be connected from. When the work lands, review it file by file in the built-in diff view, then commit, push, and open pull requests through the Git and GitHub integrations without leaving the app. A real terminal sits beside the chat, and projects, settings, and scheduled tasks stay attached to the machine where the code actually runs. Install it as a background service and reach it from anywhere through T3 Connect, a Tailscale or LAN pairing, or the hosted web client, with a pairing code guarding local access. Outside agents can also drive threads over MCP, launching, messaging, and waiting on work across machines you have linked together. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Moltis gives individuals and teams a completely private personal AI agent server that bridges conversational assistants to everyday messaging platforms while executing real-world computing tasks inside secure execution environments. Users can interact with autonomous agents across Telegram, Discord, WhatsApp, Slack, Matrix, and browser interfaces to draft correspondence, automate research, and schedule recurring cron tasks. The system coordinates multi-agent delegation by spinning up specialized sub-agents with dedicated roles for code generation, pull request reviews, quality assurance testing, and technical documentation. Built-in sandboxing isolates tool operations within container boundaries or WebAssembly modules, ensuring shell commands, web scraping routines, and script executions cannot alter underlying operating system files without explicit permission. Native Model Context Protocol integration allows operators to attach external data endpoints, database connectors, and custom command-line utilities without rewriting core routing logic. Persistent memory preserves conversational context and document embeddings across multiple sessions, allowing assistants to recall prior discussions, user preferences, and project guidelines indefinitely. Administrators can configure granular tool approvals, manage WebAuthn passkey authentication, and review real-time WebSocket communication logs through an embedded control panel. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Bisibility puts your Google rankings, keyword research, and backlink profile in one application that runs on your server instead of behind a per-seat subscription. Track every keyword by market and device, watch positions move over time, and open the stored snapshot of the actual results page behind any check to see exactly what Google showed. Alerts flag the movements that matter, while competitor share of voice shows whose visibility is growing at your expense. The keyword explorer surfaces suggestions with search volume, trends, cost per click, difficulty, and intent, and shows the estimated price before a lookup runs, so research never surprises your wallet. Backlink and domain views break down referring domains, anchors, and new and lost links next to estimated traffic and top pages for any site you type in. Search Console clicks, impressions, and queries are kept beyond the usual retention window, and a recurring prompt tracker follows how AI answer engines cite your brand over time. Results flow outward through a versioned API, MCP access, signed webhooks, and CSV exports. 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.

Running AI agents in production takes more than a model call: Omnara supplies the durable runtime, tools, approvals, and complete event history around any model, on your own machines. You define an agent once in a small YAML file: instructions, a model from OpenAI, Anthropic, OpenRouter, Bedrock, LiteLLM, Ollama, or your own endpoint, and the machines it may use. Launch agents from the REST API, the TypeScript SDK, the command line, or the dashboard, then stream every event live or receive it as a webhook while the agent works. Agents run shell commands and edit files on sandboxes from twelve providers, or on your own laptops, VMs, and containers through a daemon that connects outward, so no inbound ports or SSH keys are exposed. Every step is written to Postgres as an event log, which means an agent survives crashes, restarts, and disconnected machines and resumes exactly where it stopped. Tool permissions can run immediately, ask a person first, or block outright, and agents can start subagents, follow cron schedules, and keep shared memory files between conversations. Teams meet the agents where they already talk: mention the bot in Slack or Discord, or let a GitHub pull request trigger a review, with questions and approvals handled in the thread. 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.

Claiming 60-80% token cost reduction compared to flat single-model deployments and backed by 6,500+ GitHub stars, OpenSquilla delivers an intelligent AI agent runtime where a local ML classifier evaluates every turn on message length, code blocks, keyword patterns, and semantic embeddings before routing it to the optimal model tier from C0 through C3. The pluggable provider layer connects natively to TokenRhythm, OpenRouter, OpenAI, Anthropic, Ollama, DeepSeek, Gemini, DashScope, Moonshot, Mistral, Groq, Zhipu, SiliconFlow, vLLM, LM Studio, and additional compatible backends with primary-plus-fallback selection. The four-tier cognitive memory architecture spans working, episodic, semantic, and raw layers with vector-semantic and BM25 retrieval powered by on-device ONNX embeddings that never leave your infrastructure. Security isolation operates at the syscall level via Bubblewrap on Linux and Seatbelt on macOS, complemented by policy-based execution controls and prompt injection protections. The unified TurnRunner executes identically across the Vue-based control console Web UI, terminal CLI, and chat channel integrations including Slack and Discord, ensuring consistent tool dispatch, retry logic, and decision logging regardless of entry point. Built-in skills cover deep research, multi-search-engine queries, document generation for DOCX, PPTX, XLSX, and PDF formats, GitHub integration, cron scheduling, and bounded subagent delegation. Per-agent workspaces with durable session storage provide transcript replay, context state management, and per-call cost tracking with automatic quota enforcement. 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 nearly 8,000 GitHub stars since its December 2024 launch, Kaneo has rapidly gained traction as the minimalist alternative to bloated project management platforms like Jira and Linear. Built on TypeScript with React and Hono, the interface strips away complexity to focus on execution — plan in list view, track in kanban board, and schedule on interactive Gantt chart timelines where dragging bar handles adjusts start and due dates with optimistic UI updates. Native GitHub integration synchronizes issues bidirectionally, links pull requests to tasks, and keeps product planning aligned with development execution without context switching. The built-in Model Context Protocol server at /api/mcp enables AI tools like Claude and Cursor to manage tasks, projects, and labels directly, while the official @kaneo/mcp npm package provides stdio access for local MCP clients. Authentication supports password, magic link, GitHub OAuth, and Google sign-in with organization-level access management. Rich text editing for task descriptions and comments, label-based initiative grouping, priority levels, assignee management, and due date tracking provide focused planning without ceremony. Deploy with the drim CLI for automatic HTTPS and database setup, Docker Compose for custom configurations, or Helm charts for Kubernetes clusters — all requiring just 2GB RAM and PostgreSQL. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Wire nodes together in a browser, deploy in one click, and real-time data flows from sources through transformations to outputs: Node-RED is the OpenJS Foundation's flow-based programming tool for event-driven applications. Born at IBM as a proof-of-concept for manipulating MQTT topic mappings, it has become the lingua franca of IoT and automation glue - home automation, industrial control, edge data collection - with a community library of over 5,000 contributed nodes and flows covering protocols, devices, and services. Where visual wiring runs out, JavaScript function nodes written in a rich in-editor code editor take over, and every flow serializes to importable, exportable JSON that shares cleanly and version-controls sensibly. Version 5.0 (2026) delivered the largest editor overhaul in the project's history: a rethought layout with Explorer and Information panels in a split sidebar, a native dark theme with theme variants, improved accessibility, and refreshed node appearance. The runtime is lightweight Node.js, exploiting the event-driven non-blocking model so the same flows run on a Raspberry Pi at the network edge or a cloud VM. Apache-2.0 licensed with 240+ contributors, it pairs naturally with dashboard nodes for live charts and controls.

A clean alternative to n8n and Zapier that puts AI-native workflows front and center, Fynt is the MIT-licensed workflow automation platform where you drag nodes onto a React Flow canvas, wire them together with typed connections, and let a distributed BullMQ engine execute them — with every step streamed live to your browser over WebSockets so you never wonder what happened inside a run. The node library spans triggers (manual, webhook, cron scheduling), AI providers (OpenAI, Anthropic, and Gemini with structured output parsing), service integrations (GitHub webhooks, Notion databases, Slack channels, Discord bots, arbitrary HTTP endpoints), logic gates (conditional branching, filtering, data transformation), and utility nodes (delay, logging, payload mapping). The execution architecture separates concerns across three services: a Next.js 16 web application serving the React 19 workflow builder and tRPC API, a BullMQ worker processing jobs with node-level retries and checkpointing for crash-safe execution, and a dedicated WebSocket relay server broadcasting real-time run events via Redis Pub/Sub. All stored credentials are encrypted at rest using AES-256-GCM with per-credential initialization vectors. The full-stack deploys as a single Docker Compose stack (web, worker, realtime, PostgreSQL, Redis) or individually via pnpm workspaces in a Turborepo monorepo. Authentication is handled through better-auth with configurable OAuth providers. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.