SuperAPI AI Directory
Partner with us中文AI newsFavorites

AI agents

2,941 results · Page 40 of 82

claude-consensus

AI agents

claw-consensus (formerly claude-consensus) is a reference implementation of a multi-machine coordination layer for running AI agents on multiple machines and avoiding state drift. Through a consensus protocol (propose/counter/accept/commit), a dual-track message bus, ACK acknowledgment discipline, and self-healing synchronization mechanisms, it enables agents on different computers to negotiate decisions, commit results, and verify each other, waking humans only when money or irreversible operations are involved. The project is implemented purely with the Python standard library, requires no additional packages, servers, or databases, and is free and open source under the MIT license.

Read more

claude-lens

AI agents

claude-pace (repository name claude-lens) is a lightweight Claude Code status bar and rate limit tracking tool that displays 5-hour and 7-day quota usage in real time in the terminal, along with a reset countdown. Its biggest feature is "pace-aware" quota monitoring: it not only tells you how much you have used, but also compares the current consumption rate with the remaining time in the window, using ⇡ or ⇣ to show whether you are overspending. The tool is written in pure Bash + jq, is a single file, has zero npm dependencies, and can be installed via the Claude Code plugin, npx, or a script.

Read more

claude-snapshot

AI agents

claude-snapshot is a portable configuration snapshot tool for Claude Code that exports your configuration, plugins, hooks, and global instructions as a .tar.gz snapshot file and quickly applies it on another machine. It supports scenarios such as multi-machine synchronization, backup before system reinstallation, safe rollback, and team onboarding. By design, it adheres to a minimal footprint (no daemon, no background listening), allowlist collection, never connecting to the network, diff before overwrite, and cross-platform first (Node.js implementation). It requires Node.js 18+, can be used as a Claude Code plugin, and can also be run via npx without installation. Current version v0.2.

Read more

claudeclaw

AI agents

ClaudeClaw is a persistent agent orchestration plugin based on Claude Code, originating from the NanoClaw project. It provides a continuously running message loop that listens to channels such as Slack, WhatsApp, and Telegram, routes messages to Claude agents running in isolated sandboxes, and maintains ongoing conversations through structured memory management. Core features include multi-channel routing, thread management, context accumulation, Webhook triggers, per-group agent configuration, cost tracking, an extension system, and OS-level sandbox isolation based on Anthropic sandbox-runtime (Seatbelt on macOS, bubblewrap on Linux), with container runtimes also supported. The project runs as a Claude Code plugin, the current directory is the instance, state files are stored in the working directory, the codebase is small enough to fit into a Claude context window, and it emphasizes customization through code modifications rather than configuration files.

Read more

clawbot

AI agents

Clawbot is a decision layer directory for the agentic web, helping users match a task with the right agent, the tools it needs, and the access it should have before connecting any agent. The site catalogs 164 agents and 51 MCP servers, presenting them through task matching, traceable sources, permission descriptions, and maintenance date labels. Starting from a target outcome, users can obtain an inspectable agent stack combination covering areas such as coding, research and browsing, operations automation, and system connectivity. The directory does not use paid rankings, and official sources always remain the final authority.

Read more

ClawFleet

AI agents

ClawFleet is an open-source multi-agent deployment and management tool for running two types of AI agents, OpenClaw and Hermes, as Docker containers on a personal Mac or Linux machine, managed centrally through a browser dashboard. The official description states that deployment can be completed in about 10 minutes (the introduction also mentions 5 minutes), supports using a ChatGPT subscription, and requires no cloud fees. Each instance has an independent file system and network isolation, can connect to model providers such as OpenAI, Anthropic, Google, and DeepSeek with a single API key, and offers capabilities including a role system, skill management, Soul Archive soul archive cloning, clawfleet shell terminal access, and version locking.

Read more

ClawManager

AI agents

ClawManager is a Kubernetes-native AI agent instance management control plane, designed for platform teams that need to run AI agent instances for multiple users. It provides governed AI access, runtime orchestration, and reusable resources across multiple agent runtimes, supports managed runtimes such as OpenClaw, Hermes, OpenCode, and DeepSeek Harness, and offers two deployment modes: Lite and Pro. Users work through a browser-based desktop, while administrators can perform visibility and policy control without exposing Kubernetes details. The platform also includes capabilities such as AI Gateway model governance, Agent Control Plane runtime orchestration, team collaboration, resource management, a skills center, and a security protection platform.

Read more

Cleanlab

AI agents

Cleanlab is a tool that helps teams build safer AI agents, with the core goal of preventing erroneous responses from reaching users. It can detect and fix erroneous responses generated by any AI agent, thereby ensuring safety, compliance, and trustworthiness at scale. Built by an industry-recognized team, the tool is trusted by startups and large enterprises. Deployed as an independent layer, it adds safety, control, and trust capabilities to AI systems without modifying the existing tech stack. It provides real-time trust scoring and guardrails, smoothly escalates from AI to human support, helps teams optimize answers, sources, and guardrail policies, and supports no-code improvement of AI applications. Deployment is flexible: it can be privately deployed in your own cloud, and it also supports secure, seamless access without managing infrastructure.

Read more

clideck

AI agents

CliDeck is a dashboard that runs and coordinates multiple AI CLI agents in a local browser window. It supports running Claude Code, Codex, Gemini CLI, OpenCode, Pi, and shell sessions simultaneously, can group them into projects, track progress, and resume conversations. Each session is the agent's real terminal, with its own tools, configuration, and account. The interface shows projects and sessions on the left and the selected agent's terminal on the right, with message previews, unread counts, and activity times, similar to a WhatsApp conversation list. Agents can open their work artifacts directly in CliDeck for viewing and feedback. Node.js 22.12+ and the corresponding agent CLI must be installed, and it is accessed via a local address or run with npx.

Read more