Respan Gateway screenshot thumbnail

Respan Gateway

Respan Gateway is a single-binary LLM gateway that lets the SDK you already use call any AI model from any provider, translating between OpenAI, Anthropic, and Gemini API formats on the way through. Point an OpenAI, Anthropic, or Gemini client at it and you reach chat models on sixteen providers, plus any OpenAI-compatible endpoint of your own, with streaming, tools, images, and reasoning translated. Traffic control works the way operators think: name a route, send it to the cheapest or fastest provider, retry on failure, fall back to a second vendor, or hedge a slow call by racing another provider. Models that never had tools get them anyway, because MCP servers and built-in search, browsing, code, document, and memory tools run inside ordinary chat requests behind the gateway. Realtime voice crosses vendors too, with an OpenAI Realtime client able to talk to Gemini Live, alongside images, speech, transcription, embeddings, and video through one endpoint. A live request log in the web UI shows the client key, model, provider, status, tokens, cost, and latency of every call, so runaway agents and surprise bills are visible immediately. Everything is a plugin on one public Rust API, from routing and pricing to tracing, with examples for guardrails, PII masking, and billing. One TOML file configures keys, providers, routes, and tools, validates before it starts, and reloads on signal. 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.

Deploy
LiteLLM Agent Control Plane screenshot thumbnail

LiteLLM Agent Control Plane

Agents scattered across vendor consoles become one tidy workspace in LiteLLM Agent Control Plane, which puts Claude Managed Agents, Cursor, OpenCode, OpenClaw, Deep Agents, and Hermes behind a single login, one API, and one dashboard. Describe an agent in plain language or start from a template for a deep researcher, an inbox triager, or a security reviewer, then tick the tools, skills, and MCP integrations it may use and pick the runtime that executes it. Chat happens inline with streamed output, sessions persist across runs, and a memory layer carries context from one session to the next. Routines launch agents on a cron schedule, and each scheduled run lands in the history as its own session. An MCP proxy injects upstream credentials at the wire, so agents never hold real secrets, and provider keys sit encrypted in a vault. Colleagues can reach the same agents from Slack, Microsoft Teams, Google Chat, or a webhook, and developers can drive everything through a REST API with a live try-it reference. Administrators issue per-user virtual keys with budgets, model limits, and expiry dates, and an inbox gathers anything that needs a human decision. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Deploy
Archestra screenshot thumbnail

Archestra

Archestra delivers the enterprise AI infrastructure layer that organizations need when managing multiple LLM providers, MCP servers, and AI agents across teams becomes unmanageable. The LLM gateway routes requests across Anthropic, OpenAI, Azure, Bedrock, and DeepSeek with virtual API keys, per-team cost limits, and dynamic model routing — giving every developer one token for Claude Code, Cursor, or Codex while finance tracks spend per department. The MCP gateway authenticates tool calls with OAuth 2.1 and On-Behalf-Of tokens so each tool executes as the calling user, not a shared service account, eliminating credential sprawl. The private MCP registry lets teams publish custom tool servers with approval flows promoting servers from dev through staging to production, each environment maintaining its own credentials and network egress policies. The Kubernetes operator manages MCP server lifecycle — deploying containers, scaling, health-checking, and routing gateway traffic to local servers automatically. The agent runtime supports scheduled triggers, email and webhook invocations, sub-agent delegation, reusable skills, and sandboxed code execution with a K8s-native filesystem. Deterministic guardrails including Dual-LLM verification and Lethal Trifecta protections prevent dangerous tool calls before execution. Built-in OpenTelemetry traces and Prometheus metrics provide full observability without additional tooling. Docker deployment exposes the Admin UI on port 3000 and API on port 9000 with a single command. 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.

Deploy
Bionic screenshot thumbnail

Bionic

Bionic gives a company its own private AI workspace where models can read documents, use approved tools, run code, and hand back finished files. Staff open a chat, pick a model, and ask for work; the agent searches datasets, calls connected systems including Gmail, Google Drive, Salesforce, ServiceNow, and Jira, and saves spreadsheets, reports, and PDFs as artifacts. Skills package reusable instructions for jobs like release readiness, incident briefings, policy gap reviews, and RFP responses, so a good workflow gets written once and reused by everyone. Datasets collect security policies, product docs, handbooks, and support archives for grounded answers. Administrators manage API keys, watch token usage and request charts, set rate limits, configure providers, and divide people into teams with their own assistants. SSO, role-based access, and an audit trail keep the rollout governed. Developers can issue model and assistant keys and turn any OpenAPI specification into a new integration. 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.

Deploy
llama-swap screenshot thumbnail

llama-swap

llama-swap puts one OpenAI-compatible and Anthropic-compatible endpoint in front of all your local models and loads whichever one each request names, unloading the one it replaces. Define models in a single YAML file, and chat, embedding, speech, transcription, and image requests reach the right backend automatically. The web UI includes a playground for chatting with any model, token metrics for every request, a request inspector that shows raw payloads and responses, buttons to load and unload models by hand, and a live log stream for the proxy and each upstream process. Profiles switch model routing at runtime, a swap matrix keeps selected models loaded together, and a time-to-live setting frees memory after idle periods. API keys restrict who can call the endpoints, and filters strip or force request parameters. Docker and Podman commands start and stop containers per model, and a Prometheus endpoint exposes system and GPU metrics. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Deploy
9Router Pro screenshot thumbnail

9Router Pro

One endpoint for every model account you own: 9Router Pro sits between your applications and a fleet of LLM providers, decides which account answers each request, and keeps the whole operation visible on a live dashboard. Its signature trick is prompt injection scoped three ways, globally, per API key, or per model, delivered either as a system prompt or as a scripted chat history that primes the model far harder than instructions alone. Keys are products here: each carries a rolling token budget over 24 hours, 7 days, or 30 days plus rate limits per minute, hour, and day, so a resold plan enforces itself with polite 429 responses. Routing stays healthy on its own, with accounts tiered as clean, suspect, or cooldown, least-recently-used spreading across the fleet, flaky upstream responses retried against the next account, and proxy pools health-checked with one-click cleanup of the dead. The monitoring dashboard leads with VPS specs, fastest and most-used providers, top API key, and usage spectrum charts, while backup and restore cover providers, combos, keys, and settings section by section. Everything runs as a single application with one SQLite file and a dashboard localized into 34 languages. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Deploy
PicoClaw screenshot thumbnail

PicoClaw

An 8MB Go binary that boots in under one second, uses less than 10MB of RAM, yet delivers full AI agent capabilities across 16+ chat platforms simultaneously. PicoClaw connects to Telegram, Discord, Matrix, IRC, Slack, WeCom, DingTalk, WeChat, LINE, and QQ while supporting LLM providers spanning OpenAI, Anthropic, Gemini, DeepSeek, AWS Bedrock, Azure, and local models via Ollama. Native Model Context Protocol support enables standardized tool integration, and the built-in smart routing engine directs simple queries to lightweight models to reduce API costs while sending complex tasks to capable models. Tool capabilities include secure shell execution, filesystem access, web search, cron scheduling for recurring tasks, and sub-agent spawning with status tracking. Gateway mode transforms PicoClaw into a full AI backend with REST API endpoints accessible from any client. The Skills system loads hierarchical behavior definitions from SKILL.md files, enabling customizable agent personalities and workflows. Compiles for x86_64, ARM64, ARMv7, RISC-V, MIPS, and LoongArch, making it deployable on hardware as cheap as a $10 Sipeed LicheeRV Nano. Achieved nearly 30,000 stars within six months of its February 2026 release. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Deploy
Liaison screenshot thumbnail

Liaison

Liaison puts every private service you run behind one browser console, so a laptop, a homelab box, or a customer server becomes reachable without opening a single inbound port. Install a lightweight connector on each device and it dials out to the control plane, where administrators register applications over TCP, HTTP, HTTPS, WebSocket, and SSH and grant access per user. Browser workspaces cover audited Web SSH terminals, RDP and VNC desktops, SFTP file management, read-only S3 browsing, and database clients for MySQL, PostgreSQL, MariaDB, SQL Server, Oracle, MongoDB, and Redis, each with a session Agent that drafts commands and explains query results once you approve them. Local models are shared through authenticated APIs with a browser Playground, scoped keys, token quotas, and usage tracking, while Codex and Claude Code run on your own devices with resumable sessions and permission prompts. A built-in code-server IDE edits projects remotely, and on-demand TCP ports open for 5 to 300 seconds. Casbin-backed identity management, firewall policies by source IP or CIDR, and logs of management actions and supported sessions keep access accountable. Application discovery scans connector devices for existing services and registers them 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. AGPL-3.0 licensed.

Deploy
Obsidian Arc screenshot thumbnail

Obsidian Arc

Teams and communities sign in to a private AI chat site, and one admin console routes and meters every request. Users pick a model from the menu and chat with streamed answers, visible reasoning, projects that share a system prompt, searchable history, archives, and an Image Lab for generated pictures. Administrators connect providers that speak the OpenAI or Anthropic protocols, map several models onto each, and place users in groups with their own allowances counted in requests, tokens, or credits per five hours, week, or month. A developer endpoint accepts API keys and serves chat completions, Anthropic messages, responses, images, and a model list, so coding assistants and scripts can share the same pool. The dashboard charts requests, tokens, and spend by model and by person, and Availability probes idle models and trips a circuit breaker after repeated failures. Registration can be open, invite-only, or closed, with invite codes, email rules, authenticator-app two-step sign-in, and GitHub, Google, or OpenID Connect login. Announcements, a feedback inbox, an optional leaderboard, a guest trial chat, and scheduled backups to S3-compatible storage round out the operator toolkit. A company AI portal, a classroom, a research group, or a paid community with trial codes can all run on it. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Deploy
codex-lb screenshot thumbnail

codex-lb

codex-lb turns a handful of ChatGPT accounts into one dependable endpoint for Codex CLI, OpenCode, OpenClaw, Hermes Agent, and any OpenAI-compatible client. Accounts join through an OAuth flow, and the dashboard shows each one's 5-hour and weekly quota as percent remaining, with reset times, plan, and a seven-day trend. Eight routing strategies, including capacity weighted, round robin, and sequential drain, pick an account per request, and sticky threads keep a session on the same account to preserve warm prompt caches. API keys carry expiry dates, model allowlists, reasoning-effort policies, per-account scoping, and token or cost limits per day, week, or month. Overview cards chart requests, tokens, cached share, estimated cost, error rate, and a weekly credit pace, and a searchable request log lists the model, transport, status, tokens, and cost of every call. A cost report breaks spend down by day, model, user agent, and account, with time to first token and tokens per second charts. Dashboard access is protected by a password with optional TOTP, a read-only guest mode, roles, and invites. Settings cover reset-credit handling, upstream proxy pools, model sources, a firewall, and a quota planner, and light and dark themes are built 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.

Deploy
Routerly screenshot thumbnail

Routerly

Routerly is the one front door for every AI model your apps use: point your OpenAI or Anthropic client at it, and it chooses the right model for each request, enforces your budget, and keeps the receipts. Nothing in your code changes except the base URL, and from that moment streaming chat completions and messages flow to OpenAI, Anthropic, Gemini, Mistral, Cohere, xAI or your own Ollama models behind a single token. Nine routing policies score every candidate in parallel: cheapest, fastest, healthiest, most capable, biggest context, least rate-limited, fairest, most budget left, and one that asks a small model to judge which model fits the task. When the winner errors or times out, the next candidate takes over automatically, and the recorded routing trace shows exactly why each model won or lost. Guardrails can block or log content that breaks your rules, and phone numbers, card numbers, SSNs, IBANs and emails can be scrubbed out before anything reaches a provider. Every call is logged with tokens, USD cost and latency, and hard limits per model, project and token reject overspending requests before a provider can charge for them. Projects keep separate tokens, model lists and budgets for each team or tool, role-based permissions decide who may change what, and alerts land in Slack, email, webhooks or PagerDuty when budgets or providers misbehave. 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.

Deploy
RESTai screenshot thumbnail

RESTai

Every AI project you build in RESTai becomes an endpoint that any app can call over plain HTTP. RESTai gives you a browser dashboard where each project gets its own model, system prompt, tools, and chat playground. Build knowledge-base assistants over uploaded files and synced web pages, ReAct-style agents that call MCP servers, or drag-and-drop block projects that need no model at all. Connect Ollama, OpenAI, Anthropic, Gemini, vLLM, Azure, Bedrock, or any OpenAI-compatible endpoint, and let teams share the ones you approve. Daily charts follow tokens, cost, and latency per project, with rate limits, guardrails, prompt version history, and evaluation runs for quality tracking. Teams, roles, two-factor sign-in, white-label branding, and an audit trail cover administration. A one-line chat widget embeds a project on any website, and connectors reach Telegram, Slack, and WhatsApp. One install can serve several branded assistants and bill each team separately. 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.

Deploy
LLMIO screenshot thumbnail

LLMIO

Every provider has its own API, quota, and price list, and LLMIO puts them all behind one door. Clients speak OpenAI Chat Completions, OpenAI Responses, Anthropic Messages, or Gemini, and a protocol bridge translates between OpenAI and Anthropic formats, including streaming events, when the upstream differs. Each model name maps to several providers with weights, a lottery or rotor load strategy, retry limits, and timeouts, and routing can follow tool calling, structured output, and image support. A per-model circuit breaker and rate-limit fallback keep one failing upstream from taking the rest down. The dashboard shows live requests, success rate, tokens, cache hits, retries, tokens per second, and cost, and analytics add trend, breakdown, latency, error, and model performance views with provider, key, and status filters. The request log records trace and session IDs with full request and response inspection, and a compare page lines up to six requests to show how a prompt cache builds. Access keys carry expiry dates, model allow-lists, and optional body logging. Quota sources, time-of-day pricing, and scheduled log cleanup round out the console. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Deploy
FastLLM Proxy screenshot thumbnail

FastLLM Proxy

Local vLLM and llama.cpp boxes and hosted providers like OpenRouter, Anthropic, Bedrock, and Gemini all answer to one OpenAI-compatible address once FastLLM Proxy sits in front of them. Clients ask for a frontend model by name, and ordered rules pick the target by caller, prompt size, headers, budget spent, time of day, or how busy a backend is. Prompts that share a prefix return to the node holding their cache, and semantic routing sends coding questions one way and chat another using example prompts you write. API keys carry per-model grants, rate limits, and token or spend budgets, and the management console shows traffic, usage and spend, an append-only audit log, and a fleet topology. Failures fall through to the next target before a byte reaches the caller, and an admission gate turns a flooded engine into a bounded queue. An MCP gateway and an A2A agent endpoint put tool servers and agents behind the same address. Existing LiteLLM configs import unchanged. 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.

Deploy