OpenCode puts a capable coding agent in a browser tab, so a project on your server can be worked on from any device. Start a session, describe the change, and watch the agent read files, edit code, and explain what it did in plain language. A review panel lists every changed file with unified or split diffs, a file tree, and a git changes view, so nothing lands without a look. Sessions open as tabs, run in parallel, and keep a searchable history per project. The model picker spans more than 200 providers plus free hosted models, and any OpenAI compatible endpoint can be added from a config file, which keeps local and self-hosted models in reach. Settings offer top tabs, side tabs, or an inbox layout, optional permission auto-accept, steer or queue behavior for follow-up prompts, timeline detail levels, themes, and fonts. Extensions cover MCP servers, plugins, and skills, and custom agents and commands capture the team's habits. One-time pairing links connect a new browser or app to the server in seconds. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Open-weight language models get a private chat service on your own server, and llama.cpp serves its browser UI the moment the server starts. Conversations appear in a sidebar with search, and each answer shows its token count, generation time, and tokens per second, so you can see how a model really performs. Code replies render in highlighted blocks with a copy button, and messages can be edited, regenerated, forked, or deleted. A Models page lists what the server can run with context sizes and load status, and Settings cover themes, system messages, display options, tools, agentic behavior, import and export, and sampling controls for temperature, top K, top P, and penalties. Remote MCP servers connect by URL, and uploads let multimodal models read files and images. Behind the UI sit OpenAI and Anthropic compatible chat endpoints, embeddings, reranking, function calling, JSON schema constrained output, parallel decoding, and continuous batching for several users at once. Quantized models run on plain CPUs, and official images cover CUDA, ROCm, Vulkan, and other accelerators. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Comparing prompts and models by eye stops working fast, so ChainForge lays every experiment out on one visual canvas. Drop a table of inputs into a Prompt Node, add a handful of models, and the app sends every combination of template variable and model, then collects the answers in an Inspect Node that groups responses by any variable. Evaluator nodes score outputs with a few lines of code, and visualization nodes plot pass rates and numeric scores as histograms or box plots. Chat Turn nodes test follow-up questions, to see if a model caves when a user pushes back. Sparkle buttons draft synthetic table rows, test questions, and starter evaluator code with a model of your choice, and an LLM scorer can judge answers against a rubric you write. Example Flows open ready-made experiments, from a no-key starter with tiny in-browser models to prompt template comparisons, sycophancy checks, gender bias audits, red-teaming runs, and 188 flows converted from OpenAI Evals. Documents, Chunking, Retrieval, and Rerank nodes cover retrieval experiments. Finished flows export as cforge files, and results export to spreadsheets or JSON for the rest of the team. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

SandBase Harness gives your AI agents a proper home with sessions, tools, sandboxes, and an audit trail instead of a pile of scripts. The console lists agents with their model, status, and version, and an agent page shows its system prompt, attached tools, and skills. Every session keeps a resumable event log, and a transcript view opens any user or agent message as a rendered or raw event. Built-in tools run in a local process, per-session Docker containers, Kubernetes, or a self-hosted worker queue, and permission policies can always allow a tool or always ask a human first. MCP toolsets, credential vaults, and skill packages extend what an agent can reach, with Anthropic's xlsx, pptx, pdf, and docx skills listed next to your own. Memory stores, webhooks, scheduled deployments, and outcome definitions cover longer-running work. Settings include a model provider form, API keys for bearer authentication, and an interactive API reference for sessions, agents, environments, and vaults. A TypeScript SDK and a bundled MCP bridge connect other tools to the same runtime. 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.

Evidently gives your models and LLM apps a proper check-up and keeps every result on one shared dashboard. Project dashboards chart predictions against targets, data drift, and quality scores over time, with counters for model calls and the share of drifted features. A reports page lists every evaluation snapshot with tags, metadata, timestamps, and view or download buttons, and a search box filters them by metadata. Over 100 built-in metrics cover data quality, classification, regression, ranking, recommendations, text descriptors, and LLM judges. Test suites add pass or fail conditions, so a nightly job can flag a drifting feature before customers notice a bad prediction. Datasets, traces, and prompts have their own tabs, which keeps retrieval and generation experiments beside the scores they produced. Reports export as HTML or JSON for sharing outside the dashboard. Results live in a local folder, a SQL database, or S3-compatible storage, and a remote workspace accepts snapshots sent from jobs running anywhere. Built-in demo projects with bike demand forecasting and e-commerce review classification show how a finished dashboard looks before you wire in your own data. 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.

Promptfoo replaces vibes-based prompt tweaking with measurable tests, then attacks your AI app the way a hostile user would. An evaluation matrix lines up every prompt and model side by side, with pass or fail badges, assertion messages, latency, token counts, and cost in each cell. A red team wizard walks through the target, application details, plugins, and strategies, then probes for prompt injection, data exposure, broken access control, and harmful content. Preset bundles map plugins to the OWASP LLM Top 10, NIST AI RMF, MITRE ATLAS, GDPR, ISO 42001, and the EU AI Act. Meta Agent and Hydra Multi-Turn strategies adapt attacks across a whole conversation instead of firing one-shot prompts. Providers span OpenAI, Anthropic, Gemini, Bedrock, Azure, and local Ollama models, and any HTTP endpoint, Python script, or JavaScript function can be tested as a target. The history page lists every run with pass rates and raw scores, and prompt and dataset pages show which templates and test sets each run used. A provider allowlist file narrows the models offered in the web editor for cost control. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

An AI agent that maps your attack surface, proves what is exploitable, and drafts the code fix: RedAmon is a red team for domains you are authorized to test. A six-phase recon pipeline runs subdomain, port, HTTP, and vulnerability scanners in parallel and merges every result into a Neo4j graph you can query in plain language. The agent works from a Kali sandbox with 100+ security tools, asks for human approval before risky steps, and can deploy a Fireteam of specialist sub-agents that investigate separate angles of one target at once. CypherFix triages each finding, then a code agent opens a GitHub pull request with the patch. AI Gauntlet attacks chatbots and LLM endpoints with prompt injection and jailbreak batteries, mapped to the OWASP LLM Top 10. TrafficMind records every HTTP request the tools send, with a searchable history the agent can replay. An Insights dashboard charts findings, CVE severity, and attack chains per project, and the settings page connects OpenAI, Anthropic, OpenRouter, Bedrock, or local Ollama and vLLM models. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Give an outcome to Lucy, the built-in steward, and she assembles a fresh team of role-based agents inside a channel, with separate sessions and memory for each one. An official template library covers content, data, design, developer, legal, marketing, operations, product, and strategy workflows, from API documentation teams to pull request reviewers. Messages turn into Kanban tasks that agents claim, split into subtasks, submit for review, and close, and each task keeps its thread attached. A channel team graph shows who assigns work to whom, and Thinking mode branches a discussion into focused lines of reasoning that return conclusions to the parent. Agent Live tracks working, idle, and timed-out agents with a transcript viewer for every session, and an Insight dashboard charts messages, runs, tasks, and token usage over time. Finished work becomes artifacts you can review, regenerate, and publish. Pair a laptop or server as a Computer with a one-time command, and an inbox gathers mentions and replies. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

NextClaw is an AI workspace where a request for a report, a chart, or a small tool becomes organized research, files, and steps, with the result shown beside the conversation. Pick the engine for each task from Native, Claude Code, Codex, Hermes, or OpenCode, and the agent keeps its memory, skills, and workspace. A right-hand browser opens code, Markdown, HTML, Word, Excel, and PowerPoint files without losing the task that produced them. Connect providers like OpenRouter, OpenAI, Anthropic, Gemini, DeepSeek, or any OpenAI-compatible endpoint, and message the same agents from Telegram, Discord, Slack, WhatsApp, Feishu, or email. Scheduled tasks start from templates like a daily AI news brief or a competitor change tracker, and finished reports land in an AI Inbox you can read later or continue as a chat. A skill market installs new abilities, MCP servers extend tools, and Panel Apps keep the small pages an agent builds for you. Dedicated agents get their own role, home directory, and memory. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

PenguinHarness turns a one-sentence description of the agent you need into a working app, then lets other agents tune it round after round until its benchmark score climbs. Nine self-improvement algorithms ship as plugins, including OPRO, APE, ACE, and AWM, and every candidate becomes a snapshotted version with its score recorded in an Evaluation Center. Seventeen ready-made benchmarks cover data analysis, repository fixes, workflow automation, and terminal science tasks. Agents read and act on web pages through a built-in browser panel or your own Chrome, and each agent can grow a hot-reloaded workbench page like a contract review desk with uploads and downloadable reports. Add a machine over ssh and conversations in that workspace run there, inside the same window. A Cost Center breaks down spend per run, trajectories show every turn on an execution timeline, and replies can carry forms, charts, and live widgets. An Agent API streams runs to outside apps, and agents can be reached from Feishu, QQ, Telegram, or WeChat. 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.

Put a checkpoint in front of every tool call your AI agents make, so a poisoned web page or file cannot quietly move money or send private data. Each call is classified and policy-checked before it executes, then allowed, blocked, or held for a person. Held calls land in an approvals queue that shows what the user asked, which passage the agent read, and the exact recipient or amount in question, with one-click block or allow. Instruction provenance flags destinations that appeared only in untrusted content, like an IBAN hidden in a file. The cockpit lists every run as a timeline of steps with verdicts, groups violations by the protection that caught them, and scores ten attack surfaces on a Security 360 page. An agent registry tracks owners, scope, and call counts. Budgets, anomaly alerts, and a kill switch cap runaway behavior. Sensitive values are redacted from traces, signed receipts prove a call was allowed, and exports produce PDF and CSV audit evidence. Python and TypeScript SDKs plug in with one line, or an LLM proxy catches calls with an environment variable. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Thirty model providers, one OpenAI-compatible endpoint: Ferro Labs AI Gateway routes every request from your applications to the provider that should answer. Eight routing strategies cover fallback chains, weighted load balancing, lowest latency, lowest cost, content-based rules, A/B tests, and conditional targets, each with retries and circuit breakers. Guardrail plugins filter blocked words, redact personal data, scan for leaked secrets, block prompt injection, validate response schemas, and enforce rate limits and per-key spend budgets. Identical prompts can come back from a response cache, and tool servers connect through MCP so the gateway can run the tool-call loop itself. The console opens with a getting-started checklist, then charts traffic, token throughput, latency percentiles, and cost by model. Providers, routing targets, and plugins each get their own page, a playground sends test chats through the real routing path, and request logs plus an audit trail record who changed what. Scoped admin and read-only keys give every operator separate access, and configuration history allows a rollback. OpenTelemetry traces and Prometheus metrics feed existing 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.

Every job gets its own AI teammate in Lemma, shared with your whole team and busy building the pages, tables, workflows, and apps the work needs. Each teammate lives in its own space, so the briefs it writes, the records it keeps, and the screens it builds stay where your people can open them instead of vanishing up a chat thread. Agents run when asked and also on a schedule, a table change, or an incoming webhook, with every run recorded step by step. Before anything consequential, like sending an email or issuing a refund, the run pauses and asks the person who owns the decision. Workflows hand work between agents, plain code, decisions, loops, and named people, and a run can wait days for an approval. Teammates keep memory as Markdown notes that anyone can open and correct. People reach them from Slack, Microsoft Teams, WhatsApp, Telegram, or email, and one permission model covers roles, rows, and approvals everywhere. Bring a Claude Code or Codex subscription, a hosted model, or any OpenAI or Anthropic compatible key. 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.

Give every team, project, and application one governed door to AI models instead of scattering raw provider keys across codebases. TokenHub is an OpenAI-compatible gateway that serves chat completions, responses, embeddings, reranking, and image generation, plus Anthropic Messages endpoints, in front of OpenAI, Azure OpenAI, Anthropic, Gemini, DeepSeek, Qwen, Codex subscriptions, local models, and more than 150 provider templates. Administrators publish a model catalog and write routing policies with priority, weight, failover order, and cost or quality preferences, so a provider outage never reaches client code. Users create project-scoped API keys with quotas and concurrency limits, team leaders manage project spaces and members, and each role gets a workspace that matches its job. Usage analytics and request logs attribute every call to a user, project, team, model, and cost center, and provider reconciliation compares internal usage with upstream bills. Sign in through OAuth or OIDC, control access with RBAC, and keep an audit trail of administrative changes. The console switches between English, Chinese, Japanese, and Russian, and includes an API documentation workspace for developers. 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.

AgentConnect brings Claude Code, Codex, Grok Build, DeepSeek, and any other ACP-compatible coding agent into the chat channels and repositories where your team already works, each with a role of its own. Mention an agent in Slack, Microsoft Teams, Google Chat, Lark, Discord, or Telegram and it replies in the thread, calls on a colleague agent when needed, and keeps its session visible to teammates who can step in. Work can also start from a GitHub, GitLab, Gitea, or Azure DevOps pull request, a Linear issue, a webhook, or a schedule. The web console organizes the fleet into Agents, Sessions, Schedules, Tools and Skills, Knowledge, and Daemons views. Every agent gets its own memory, skills, MCP servers, workspace, and sandbox policy, and reviewed Knowledge pages can be published for all agents to search. Decisions route new conversations to specialist agents and pick the runtime and model for each session. Review bots can run several reviewers with separate instructions on one pull request. Set who may see each agent or session, which repositories it can touch, and which agents it may call. 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.

Nod is a personal AI assistant with its own computer, so you can hand it an errand like chasing an unpaid invoice or cancelling a trial and watch it finish the job on real websites. One ongoing conversation follows you from the browser to Telegram and WhatsApp, and long jobs become saved tasks with live status lines on a Scheduled page. Connect Gmail, Calendar, Slack, Notion, Linear, or an n8n instance, and it reads threads, drafts the replies you owe, and prepares a one-page brief before each call. Every action that could change something is checked against your rules, and anything uncovered waits for your yes. Passwords, codes, and cards sit in a Vault that the server types into websites, so the model never sees them. Memory notes are visible, editable, and tied to the message they came from. Schedules run recurring checks like a weekly recap or a price watch that speaks up only on change. Usage lists every action with costs and a monthly spending limit. Pick OpenAI, Anthropic, Gemini, OpenRouter, Bedrock, or a local Ollama server as the model. 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.

Teams that juggle a file drive, a chat app, a task tracker, and a dashboard tool can fold all four into one self-hosted workspace. Twigex stores files on local disk or S3-compatible storage, shares them with users, groups, or public read-only links, and opens office documents in EuroOffice or Collabora for simultaneous editing. Chat offers channels and direct messages with reactions, mentions, and link previews. Video calls and scheduled meetings run through LiveKit, and guests can join a channel by link. Projects organize work as tables of tasks with custom fields and subtasks, viewable as a grid, kanban board, Gantt timeline, or calendar. Collimato, the analytics module, connects to databases and APIs, models the data, and builds charts and dashboards with filters and KPI cards. The admin area covers users, groups, roles, storage backends, SMTP, office editing, and security settings. The Community Edition is free to run from one binary, a Docker Compose stack, or a Helm chart on Kubernetes. 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.

Taking notes and publishing a website usually need two different tools, but W treats them as the same act. Every page you create gets its own address, and a privacy level marks it public, private, or not yet published. The editor offers tabs for Markdown content, CSS, a custom body template, and JavaScript, with a metadata panel for title, description, tags, date, and authors. Home view lists every page with sorting, filters, search, and saved bookmarks for common queries. Two alternative views draw pages as a link graph and, for pages with coordinates, as markers on a map. A media manager organizes uploads in folders, offers a thumbnail gallery, and can optimize images for the web. Several users can work together with reader, editor, super editor, and admin roles, and optional LDAP sign-in is available in beta. Templates share layouts across pages, URL commands like add and edit speed up navigation, and an experimental API opens the data to scripts. Pages keep working even with JavaScript turned off. Everything is stored in plain files, so no database server is needed. 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.