Jev Social
AI agentsA browser-grounded social research agent that lets Jev select bounded operations, uses the socai CLI in the user's Chrome session, and generates source-linked reports.
Explore agent applications that combine a model with tools and a task loop. Start with the job you want completed, then compare access requirements, human control and how a successful result is checked.
A browser-grounded social research agent that lets Jev select bounded operations, uses the socai CLI in the user's Chrome session, and generates source-linked reports.
A Kubernetes operator for deploying and managing AI agent runtimes, with bounded self-healing that keeps LLMs out of the cluster's workload write path.
A self-hosted multi-cluster Kubernetes dashboard with an AI operations agent that connects language models to live clusters through MCP.
LoopTroop is a local AI coding orchestrator that plans work with an LLM council, runs tasks in isolated Git worktrees, and retries failures with fresh context.
A desktop command center for running multiple AI coding agents in parallel, automating sessions with event cues and playbooks, and coordinating local and remote agents.
A lead-intelligence CLI for discovering prospects and managing lead-generation subscriptions and workflows.
Mysti is a VS Code AI coding team that connects multiple agent backends and supports collaborative brainstorming, red-teaming, and persistent coding conversations.
A local-first terminal coding agent that connects to user-selected models and supports tool calling, MCP, and custom commands.
An open-source AI team workspace for persistent agent identity and memory, multi-agent collaboration, and long-running work across connected channels.
Nexus-Agent is an autonomous software-engineering agent with a self-healing execution loop, AST pre-validation, persistent rollback, and terminal and web interfaces.
Open-source Claude Code skills for SEO, GEO, Google Ads, and Meta Ads, with integrations that read live account and analytics data.
A Rust CLI-first AI agent runtime that uses model providers and MCP tools to work with files, code, and shell, with interactive, piped, daemon, WebSocket, and ACP modes.
Okto-Nexus is a local-first MCP coordination hub for multi-agent teams, with durable messaging, atomic handoffs, governance controls, and human approval.
A self-hostable personal AI assistant with autonomous browser, search, shell, office, and MCP tools, plus document RAG and a visual workflow builder.
OpenAgents is an open-source workspace where AI agents connect and collaborate, with an agent launcher, shared workspace, and support for agent protocols and SDKs.
OpenBot is an open-source self-hosted platform for running a team of persistent AI bots that wake on incoming messages, use shell, HTTP, custom Python and MCP tools, keep long term memory, and pause for human approval.
OpenClaw is a personal AI assistant that runs on your own devices and connects to messaging channels, tools, skills, scheduled tasks, and memory.
An offline web dashboard for OpenClaw that monitors agent sessions, scheduled tasks, token usage, message trends, and local system metrics.
Evaluate and select AI agent observability tools using criteria across OpenTelemetry tracing, trajectory efficiency, cost accounting, and replay debugging.
Read the guideTurn a shortlist of agent frameworks into a practical decision using task boundaries, recovery tests, integration needs and maintenance costs.
Read the guide