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.

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.

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.

Backed by Y Combinator and trusted by over 2,300 companies processing billions of observations monthly, Langfuse is the most widely adopted open-source platform for building, monitoring, evaluating, and debugging LLM applications. The hierarchical tracing engine captures every LLM call, tool invocation, retrieval step, and agent action as nested spans based on OpenTelemetry, with automatic cost calculation, latency tracking, and token usage attribution across sessions and users. Prompt Management separates prompts from code with versioned artifacts, label-based deployments, one-click rollbacks, and runtime SDK fetching with server-side caching, while linking every generation back to its exact prompt version for attribution analytics. The evaluation system supports LLM-as-a-judge scoring, heuristic code evaluators, user feedback collection, and manual annotation workflows that run automatically on production traces or against curated datasets. The Playground enables interactive prompt testing on real production inputs with side-by-side model comparison across providers. Datasets and Experiments define test cases for systematic benchmarking with comparative result visualization. Native SDKs for Python and TypeScript provide decorator-based instrumentation, while 100+ integrations cover LangChain, LlamaIndex, OpenAI SDK, LiteLLM, Vercel AI SDK, and any OpenTelemetry-instrumented framework. The analytics dashboard surfaces cost breakdowns, quality scores, latency percentiles, and usage trends across models and prompt versions. 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 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).

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.

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.

Your AI application is burning through API tokens faster than you can refresh the billing page, and you have no idea which prompt template is responsible. OpenLIT plugs that visibility gap with a self-hosted observability platform built specifically for LLM workloads. Add one line of code to instrument 90+ LLM providers, agent frameworks, and vector databases, then watch every request flow through a tracing dashboard that shows tokens consumed, latency measured, and dollars spent per call, per model, per environment. The requests view lists every LLM interaction with provider, model, cost, and token breakdown in a filterable table, while the trace detail panel lets you drill into individual spans to read the exact prompt sent and response received. Prompt Hub turns prompts into versioned artifacts you deploy, rollback, and A/B test without touching application code. OpenGround compares models side by side on the same input, so you can evaluate cost-versus-quality tradeoffs before committing to a provider. Automated evaluations run LLM-as-a-judge scoring on live production traces, flagging hallucinations, bias, and toxicity in real time. The Vault stores and rotates API keys centrally so secrets stay out of your codebase. Custom dashboards let you build drag-and-drop monitoring views with charts, stat cards, and tables backed by SQL queries against ClickHouse. GPU utilization, memory, temperature, and power metrics feed into the same platform for end-to-end infrastructure visibility. 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.

Autonomous red team execution without manual script coordination is what PentaGI delivers through a multi-agent penetration testing platform engineered for automated security assessments. Security engineers configure testing scopes, target IP ranges, domain lists, and rules of engagement through an interactive web console with real-time execution graphs. Autonomous agent personas break down high-level assessment goals into discrete tactical phases, orchestrating network port discovery, service banner fingerprinting, web application crawling, and CVE verification. Specialized agents query integrated Graphiti knowledge graphs and local vulnerability repositories to synthesize attack paths, validate exploitability, and confirm finding veracity before issuing alerts. Operators monitor live agent terminal streams, inspect sandboxed tool executions, and adjust active LLM provider routes across OpenAI, Anthropic, or local Ollama endpoints. The template editor allows red teams to compose reusable testing playbooks with customizable security prompt chains, safety constraints, and automated remediation reporting. Audit logs capture full command histories, raw tool outputs, and LLM reasoning steps to generate compliance-ready technical documentation. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Xalgorix delivers AI-driven penetration testing that proves vulnerabilities exist rather than guessing, pairing an autonomous LLM agent with an independent exploit verifier that re-exploits every finding before it reaches your report. The 22-phase methodology mirrors how a skilled human pentester works through an engagement, covering reconnaissance, subdomain enumeration, port scanning, web crawling, parameter fuzzing, SQL injection testing, XSS detection, authentication bypass, API testing, and more. Select all phases or pick specific ones per target. The platform ships with 85+ offensive security tools preinstalled (nmap, nuclei, httpx, subfinder, katana, ffuf, gobuster, sqlmap, masscan, dalfox, feroxbuster) plus 14 built-in agent tools for browser automation, terminal execution, and note-taking. Connect your own LLM provider (OpenAI, Anthropic, DeepSeek, Gemini, Groq, Ollama, or MiniMax) so no scan data or target information leaves your infrastructure. The web dashboard on port 9137 provides live WebSocket telemetry showing tool calls, agent reasoning, and findings as scans progress. A findings index with CVSS scoring and severity filters organizes results, and branded PDF reports include your company name and logo. Wildcard and multi-target scans handle red team attack-surface mapping, while source-code scanning audits repositories directly without requiring a deployed target. A REST API enables scripted scans and SIEM pipeline integration, and webhooks push notifications to Discord or Telegram. 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.

Watchtower puts AI-driven security assessments into one web console, where sessions probe your attack surface while every request, finding, and piece of evidence is captured as it happens. The AI session console follows the attack surface, session progress, tool calls, and findings as an assessment runs, so you can watch an engagement unfold instead of reading a log afterwards. A built-in proxy workflow records HTTP and HTTPS traffic history with highlighted patterns, and any captured request can be sent to the Repeater for editing, replay, and response comparison. Mobile work is covered too: connect phones over USB or wireless, capture app traffic separately from accessibility control, and import WeChat mini-program packages to configure an assessment session. A public vulnerability intelligence library can be searched by component, severity, and source and kept synchronized locally, giving assessments current context without sending your targets anywhere. Findings are managed by source, severity, and status, each linked back to its supporting evidence, and the report editor assembles them with a live preview, impact notes, and remediation guidance. The dashboard tracks assets, tasks, AI sessions, token usage, and runtime resources, and task admission is budgeted against physical memory so heavy scans do not starve the host. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. GPL-3.0 licensed.

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.

Backed by the Linux Foundation with contributions from AWS, Cisco, IBM, Microsoft, Red Hat, and Shell, Agentgateway is the first data plane built from the ground up for AI agent workloads — providing a unified Rust-based proxy that handles conventional HTTP and gRPC traffic alongside MCP tool servers, A2A agent communication, and LLM inference endpoints through a single deployment. The LLM gateway routes requests to OpenAI, Anthropic, Gemini, AWS Bedrock, and other providers through an OpenAI-compatible unified API with per-tenant budget controls, spend tracking, prompt enrichment, load balancing across multiple model endpoints, and automatic failover when providers experience outages. The MCP gateway federates multiple tool servers behind one endpoint, supporting stdio, HTTP/SSE, and Streamable HTTP transports with built-in OAuth authentication compliant with the MCP auth specification, integrating Auth0 and Keycloak out of the box. OpenAPI integration exposes existing REST APIs as MCP-native tools without code changes, enabling legacy services to participate in agent workflows. Policy-based RBAC controls which agents access which tools, while OpenTelemetry integration provides distributed tracing across agent communication chains. Deploy as a standalone binary with flat YAML configuration or on Kubernetes using the built-in controller with Gateway API support for declarative infrastructure-as-code management. 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.

SkillHub gives teams a private, npm-style registry for AI agent skills, so a useful skill package is published once, reviewed, versioned, and installed into a compatible agent from the command line. Upload a package from the web console, the CLI, or the REST API, pick PUBLIC, NAMESPACE_ONLY, or PRIVATE visibility, and track releases with semantic versions plus tags such as beta and stable. Team namespaces keep their own members with Owner, Admin, and Member roles and publishing policies, while full-text search filters by namespace, downloads, ratings, and recency and hides whatever a user may not see. Every submission enters a review queue: namespace admins approve or reject team skills, platform admins decide promotions to the global scope, and each governance action lands in the audit log. A built-in Skill Scanner inspects published packages and shows its report on the skill page, with optional behavioral, LLM, VirusTotal, and Cisco AI Defense engines. Members can star and rate skills, follow download counts, receive notifications, and report problem packages. Skill suites bundle several skills into one versioned collection with an entry skill, scoped API tokens serve the CLI and scripts, and the interface speaks English, Simplified Chinese, Russian, and Korean. Packages live on local disk or S3-compatible storage such as MinIO. 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.

Enterprise security stacks assume an enterprise budget; Wildbox assumes a server you already own. It runs your whole security operation as a set of cooperating services behind a single HTTPS gateway: threat intelligence collectors pull indicators from seven public feeds on a schedule, starting with abuse.ch's Feodo Tracker, and every indicator is searchable in one place. Fifty-two security tools sit behind one API, covering DNS, TLS, email security, headers, and port analysis. The cloud posture service runs 22 configuration checks against your live AWS accounts and keeps each scan's report, while the vulnerability service inventories your assets, prioritizes findings by risk, and tracks them through remediation with SLA checks and alert rules. When something needs doing, YAML playbooks execute response workflows as background jobs, and the agents service writes Claude-generated threat-enrichment reports for suspicious indicators when you give it an API key. An osquery-based sensor streams endpoint telemetry from your hosts into the platform, kept separate per team. Users, teams, roles, and scoped API keys live in the identity service, and the backends accept nothing that did not arrive through the gateway, so your security data never leaves hardware you control. Optional Compose profiles add n8n automation and Prometheus monitoring. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT 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.