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.

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.

Before an AI agent meets real users, put it through a security checkup it cannot sweet-talk. DodoGuard is a web console and command line where teams register their agents, run evaluation and red-team tasks against them, and decide if each one is cleared for launch. The overview page shows a security index, open risks, remediation counts, and a pipeline that runs from asset intake through detection and remediation to launch monitoring and audit reports. An asset ledger lists every managed agent with its platform, environment, and risk level. A guided wizard creates assessment tasks that pick a test library for prompt injection, instruction leakage, tool misuse, and output risks, then runs black-box conversations against the agent. Evaluation configs cover prompts, providers, variable cases, and several assertion types, with OpenAI, Anthropic, Azure, Bedrock, Ollama, and any OpenAI-compatible endpoint supported. Findings land in a closed-loop board where owners confirm, fix, retest, and close each risk, and finished tasks export as reports for release evidence. Docker Compose with SQLite brings up the web UI on port 3000, and the same engine runs in continuous integration. Security teams use it for launch gates, platform owners use it for regression checks after prompt changes, and auditors use it for evidence. 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.

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.

Change an agent's prompt, model, or audience from a dashboard and watch it go live without a single redeploy. MATE opens in a Work Room where any root agent can be picked from a card grid and chatted with directly. The Studio holds the builder: a drag-and-drop canvas draws parent and child agents, attaches tools and MCP servers, and keeps every configuration versioned with one-click rollback. Trace Replay plays a past conversation back across that canvas so each hand-off is visible. A template library imports ready-made agent teams, from research pipelines to support desks. The Control Room covers governance: role-based access per agent, dollar costs per agent and project, budgets that warn or block, guardrails for personal data and prompt injection, and alerts to Slack, Discord, email, or a webhook. Eval suites score replies by exact match, similarity, or an LLM judge, and a Playground compares models or prompts side by side on score, speed, and cost. Agents can be embedded as a chat widget, called through an OpenAI-compatible endpoint, or exposed over MCP and A2A. Agencies running client agents and platform teams juggling dozens of them can manage the lot from one dashboard. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache-2.0 licensed.

To pull a team's skills, MCP servers, hooks, prompts, and agent files out of scattered Git repositories, Observal keeps them in one reviewed registry and traces real sessions to show which ones help. Build an agent visually, with a live config preview for every harness. Submissions wait in an admin review queue, where reviewers inspect side-by-side version diffs before approving a release. Teamspaces give each team its own namespace, and approved releases can be forked into independent drafts. One pull command then writes the right config for Claude Code, Cursor, Kiro, Codex, Copilot, Pi, OpenCode, Antigravity, or Goose. Every approved resource is discoverable through the open Agentic Resource Discovery standard, and a running agent can hand part of its task to another approved agent or a remote Agent2Agent service. Hooks record each session as a trace of prompts, tool calls, MCP round trips, tokens, and errors, with turn-by-turn replay for debugging and audits. Insight reports, generated through providers such as Anthropic, OpenAI, or Ollama, list what is working, what is hindering, and quick wins. A dashboard follows adoption, cost, and department usage, a leaderboard ranks agents by downloads, and audit logs, SAML single sign-on, and SCIM provisioning are included. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache-2.0 licensed.

Every team building with coding agents has the same drawer problem: the best Skill, MCP server, or agent file lives in one person's repo, undocumented, while three colleagues rebuild it from scratch. Agentic Resource Registry is the internal catalog that ends the duplication, a self-hosted registry where your organization publishes Skills, MCP servers, hooks, prompts, agent files, and sandboxes in one searchable place. Browse by teamspace, publisher, category, or harness and see at a glance what each resource supports and how often it has been pulled. Authors build agent files in a four-step builder with a live summary and draft readiness checks, then submit them into a review queue where admins inspect the full prompt and version diffs before approving. Forking an approved release creates your own draft with pinned components, and reviewers can compare it against upstream line by line. The companion CLI installs any approved resource into Claude Code, Cursor, Codex, Kiro, Copilot, OpenCode, Pi, and more, generating the correct config for each harness automatically. Approved resources are also discoverable over the open ARD standard, so a running agent can hand part of its task to another approved agent or a remote A2A service. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache-2.0 licensed.

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.

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.

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.