A hacking gym for AI apps: every lab is a chatbot or agent with a planted weakness, and your job is to exploit it and capture the flag. The dashboard tracks score, rank, badges, and a live activity feed across three tiers. Ten core labs map to the OWASP Top 10 for LLM Applications, ten advanced labs need multi-turn tactics like persona escalation, stored injection, and tool chaining, and an encrypted expert tier unlocks last. Each lab opens with a short reference panel on the weakness, offers hints, and ends with the defense that would have stopped you. Play mode uses scripted assistants so flags reproduce every time and the whole range runs offline without API keys. Live mode points attacks at a real local model through Ollama, mints a fresh secret per session, streams replies token by token, and checks the output instead of a flag box. Scenarios cover direct prompt injection, a hidden payload in an uploaded image, and unsafe rendering of model output. A RAG lab accepts text and markdown uploads, so poisoning a knowledge base is hands-on. Two themes, Neon and Phosphor green-CRT, change the look. Security teams run workshops with it, red teamers sharpen prompt injection skills, and developers see why their guardrails fail. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT 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.

Prismor sits between your AI coding agents and the tools they want to use, judging every shell command, file read, and API call before it runs so a helpful agent cannot quietly become a destructive one. Run it in observe mode to watch what agents actually do across every workspace, then switch chosen rules to enforce and block secret leaks, prompt-injection pivots, privilege escalation, and risky package installs before execution. When a call is sensitive rather than forbidden, Prismor can pause it for human approval, letting a person decide instead of the model. Plain-language prompt guardrails such as never push to main are added to the agent context per agent and per session, and edits are picked up on the next prompt. Every action lands in a hash-chained, Ed25519-signed audit trail you can verify later, while the web dashboard breaks down sessions, findings, friction, and token spend so you can see where runs went wrong. Agents that cannot be hooked are still governed through the LLM proxy or the MCP gateway, which evaluates each tool call and scans responses for injected instructions before the model sees them. Honeytoken canary files trip a critical finding the moment an agent reads them, catching reconnaissance early. 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.

Your AI coding agent has your API keys in its environment and unrestricted network access, which means one prompt injection away from sending those secrets anywhere. Pipelock closes that gap by sitting as a proxy between your agents and every outbound connection, scanning the actual content of HTTP, WebSocket, MCP, and Agent-to-Agent traffic before it leaves your server. An 11-layer scanner pipeline checks every request against 62 credential patterns covering AWS, GCP, Azure, GitHub, OpenAI, Anthropic, SSH keys, and database URLs, then inspects every response for prompt injection using 29 detection patterns with six-pass normalization that catches base64-encoded, leetspeak, and whitespace-obfuscated payloads. The MCP proxy wraps any Model Context Protocol server (stdio, HTTP, or WebSocket) with bidirectional scanning that detects tool description poisoning and mid-session rug-pull changes via SHA-256 fingerprinting. Every scanning decision produces a cryptographically signed action receipt that third parties can verify offline without trusting the agent or the vendor. The Operator Console provides a web dashboard for reviewing evidence scorecards, receipt timelines, agent sessions, enforcement decisions, and fleet posture at a glance. Cross-request taint tracking catches slow-drip exfiltration attempts that spread a secret across multiple calls. Canary tokens plant synthetic secrets that trip alerts the moment an agent tries to exfiltrate them. Pre-built Prometheus metrics and a Grafana dashboard provide real-time visibility into traffic volumes and block rates. Deploy 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.

Preloop is a self-hostable control plane that governs every AI agent tool call and model call, and can run ticket-triggered agent work that returns as reviewable pull requests. An MCP firewall can allow, deny, or hold any tool call for approval, with require-justification rules written as YAML and CEL policy. Human approvals arrive on mobile, watch, Slack, Mattermost, email, webhook, or the command line, and agents can ask a person a question before continuing. The model gateway speaks OpenAI, Anthropic, and Gemini formats, applies budgets and allowed-model lists, and attributes token spend by model, agent, session, API key, flow, and user. Flows start agents from GitHub, GitLab, Bitbucket Cloud, Jira, webhooks, or CI jobs, in hosted containers or on private runners that connect over an outbound WebSocket. Twenty-one presets review pull requests, implement issues, triage tickets, scan for vulnerabilities, and collect evidence packs. Operators can steer a running agent from the console, phone, or watch with notes, then review the resulting pull request. One session timeline records tool calls, model calls, policy decisions, approvals, spend, outcomes, and synchronized recordings. Fleet Map shows people, devices, agents, models, and observed work in one view. An account kill switch blocks gateway and tool traffic and stops managed runs, with audited recovery. 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.

Enterprises keep buying AI tools and wondering why output does not compound, when the real gap is governance: nobody can say which agent owns what, what it may touch, or what it cost. Ybkkasi answers those three questions in one console for every MCP server, skill, agent, and AI application you run. Register each asset and move it through a lifecycle state machine from discovery to retirement, with 85 permission points deciding who can view, call, publish, or approve at every step. Work itself is organized as goals that break into projects and tasks, assigned to digital employees who each carry a home organization, a human supervisor, and a roster status. Approvals route through a dedicated center where lifecycle changes and sensitive actions wait for a human decision instead of happening silently. Every call is metered, so usage and cost reports attribute spend by department, by agent, and by skill, making showback a query rather than an argument. The audit log records who did what to which asset and when, giving compliance a trail they can actually read. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT 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.

When an AI agent breaks in production, Tracely freezes that exact run into a replayable regression test and blocks the pull request that would ship the bug again. Span soup hides the failure. OTLP/HTTP traces group into conversation threads, and a waterfall marks the failing span in red with its input and output. Nobody knows if an answer was good. Evaluators sit as columns on the trace table, mixing model-free checks with LLM judges at conversation, run, or span level. Thirty-one broken runs, one issue. Clustering turns them into a single counted issue and can suggest the evaluator that would have caught it. A fix nobody can prove. One click promotes a failing trace into a hermetic case with recorded fixtures and a fail-to-pass contract, and scenarios send a red-team model after an adversarial goal. Model bills on every CI run. The suite replays offline with no API keys and no model spend, and tracely gate posts a commit status, comments on the pull request, and blocks regressions. No warning when it breaks again. Alert flows drawn on a canvas react to failed gates, broken conversations, unseen failure modes, or rising failure rates by messaging Slack, sending email, calling a webhook, or prompting an LLM. Coding agents can read traces and write evaluators through an MCP endpoint. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Every call your AI agents make becomes a searchable trace in LangWatch, and the same platform tests and scores those agents before a new prompt or model reaches users. The Trace Explorer filters by origin, user, model, cost, and evaluator, reads each run as a waterfall, flame graph, topology, or sequence diagram, and takes traces from the Python, TypeScript, and Go SDKs or any OpenTelemetry source. Agent Testing sends simulated users, in text or beta voice calls, through your agent while a judge passes or fails every criterion with its reasoning, adds multi-turn red teaming, and compares two agents side by side. The Experiments workbench scores prompts and agents on datasets with LLM judges, exact match, and RAG checks, then compares runs on cost, latency, and pass rate, while online evaluations monitor live traffic and guardrails block unsafe replies. Prompts keep version history and staging or production tags, Workflows wire prompts, Python code, and HTTP calls on a visual canvas, and annotation queues route traces to human reviewers. Alerts fire when a graph crosses a threshold, automations post to Slack, email, or webhooks, and scheduled reports go out by email or Slack. Claude Code, Codex, Copilot, Gemini CLI, and opencode report session cost, pull request cost, and terminal replays, and an MCP server exposes trace search and prompt management to coding assistants. 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.

Agenta delivers a comprehensive open-source LLMOps workspace that covers the full lifecycle of AI application development — from prompt engineering through production monitoring. The platform supports 15+ model providers including OpenAI, Anthropic, Google Gemini, Mistral, Groq, Together AI, Azure, AWS Bedrock, and self-hosted models via Ollama, enabling teams to switch between providers without code changes. The prompt playground allows side-by-side comparison of different configurations, while the evaluation system offers LLM-as-a-Judge assessment, 20+ pre-built evaluators covering semantic similarity, regex matching, and factual accuracy, plus custom Python evaluators for domain-specific requirements. Teams run evaluations through both the web UI for subject matter experts and the Evaluation SDK for programmatic CI/CD integration. The observability layer captures full trace visibility across complex agentic workflows, flagging quality issues like hallucinations and off-topic responses in real time. Human annotation workflows let domain experts review and annotate LLM outputs, feeding corrections back into the evaluation loop. The architecture supports Chain of Prompts, RAG pipelines, and multi-step agent workflows, integrating with frameworks like LangChain and LlamaIndex. Self-hosting deploys via Docker Compose with Traefik for routing, requiring only a clone, environment configuration, and a single docker compose command. On RepoCloud, deploy Agenta on a dedicated VPS with root SSH access, persistent storage for evaluation datasets and traces, and complete control over model provider credentials, all under the MIT license with no usage restrictions.

Software developers running Claude Code, Cursor, Codex, and Aider use AgentsView to trace token expenditures, search full session transcripts, and analyze multi-agent concurrency timelines. Engineers can search through historical developer sessions to locate specific code modifications, prompt chains, or debugging rationales across extensive programming workflows. The real-time activity timeline visualizes concurrent agent operations, revealing peak execution windows, task run durations, and automated tool invocations. The usage analytics engine calculates financial costs and token volumes per model by applying live pricing tables while accounting for prompt caching read discounts. Developers inspect granular turn-by-turn session transcripts complete with raw model payloads, file difference diffs, executed shell commands, and syntax errors. The recall browser extracts key technical context from past programming sessions, organizing facts into an indexed reference knowledge corpus for reuse across future project tasks. Administrators can replicate SQLite session tables into DuckDB analytics files or PostgreSQL warehouses to query longitudinal metrics using SQL analytical tools or custom reporting scripts. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

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.

Security scanners each report in their own format, and DefectDojo is the self-hosted platform that imports those reports and keeps a single, triaged list of findings. Reports in mixed formats? More than 350 built-in parsers read output from Burp Suite, ZAP, Trivy, Tenable Nessus, SonarQube, Snyk, and Checkmarx, and Generic Findings Import covers tools without a parser through CSV or JSON files. The same scan every night? Reimport adds new findings, can close the ones that vanished, and reopens the ones that return, while deduplication ties repeat detections inside an asset to their original. Decisions already made? False positive, out of scope, and risk accepted statuses survive reimport, so nobody triages the same noise twice. A deadline on every fix? Severity-based SLA countdowns flag breaches and can notify the users assigned to each asset, and full risk acceptances carry notes, files, and an expiry date that returns findings to active by default. Many teams, many applications? Organizations, assets, engagements, and tests mirror how security work is organized, with permissions that cascade downward. Pipelines that should report themselves? The REST API and CI/CD engagements import results automatically, and findings push to Jira as tickets. Someone outside security wants a summary? Dashboards track metrics, and a widget-based report builder produces HTML reports that print to PDF. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. BSD-3-Clause licensed.

For teams that need ISO 27001, NIS2, and GDPR evidence without handing compliance data to a SaaS vendor, ISMS Builder is a self-hosted information security management system for policies, risks, assets, audits, and incidents. Compliance managers move policies from draft through review to approved and archived, and recipients confirm each one through a token link that needs no login. Security officers close gaps in a Statement of Applicability that cross-maps BSI IT-Grundschutz, NIS2, EUCS, the EU AI Act, and the Cyber Resilience Act, with ISO 27001 controls imported from their own licensed copy. Risk owners keep treatment plans, turn Greenbone and OpenVAS reports into risk drafts, and score assets for confidentiality, integrity, availability, and authenticity. Data protection officers run records of processing, processor agreements, impact assessments, data subject requests, a 72-hour timer, and a deletion log with email alerts. The CISO inbox collects incidents, including reports from a public form that needs no login, beside a 30-item NIS2 Article 21 checklist and Article 23 deadline alerts. Auditors work from a findings register, a compliance matrix, and an exportable audit log of every create, update, delete, and login. Administrators enforce TOTP two-factor sign-in, choose among German, English, French, and Dutch, run semantic search locally through Ollama, and publish approved policies to Nextcloud or ownCloud as PDFs. 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.