CAMEL (Communicative Agents for Mind Exploration of Large Language Model Society) is an open-source library designed for studying autonomous and communicative agents, facilitating research in understanding their behaviors, capabilities, and potential risks through scalable techniques and cooperative frameworks, including role-playing, with extensive documentation, examples, and datasets, while also supporting integration with open-source models as backends for diverse applications
Ceki's open-source MCP server connects agents to a hosted marketplace for real-browser sessions and human services, with companion Python and JavaScript SDKs.
CerebrumKit is a self-hosted starting point for agentic projects where agents are assembled in an admin panel from skills and tools stored as database rows, with a workflow canvas and a client chat panel.
ChatDev is a virtual software company utilizing intelligent agents to revolutionize the digital world through programming, offering a highly customizable framework and integrating innovative approaches like Experiential Co-Learning, Docker support, Git management, and Human-Agent Interaction
Anthropic's Python SDK for building agents with Claude using the Claude Code harness.
ClawBench is an open-source benchmark for browser agents, with everyday tasks across live websites, execution traces, and request-level outcome evaluation.
ClawMetry is an open-source, local-first dashboard that reads existing session files from OpenClaw, NVIDIA NemoClaw, Goose, and Qwen Code. It provides agent session replay, tool-call timelines, and token and cost reporting where runtimes expose that data.
Cline is an open-source coding agent available in IDEs, terminals, and desktop, where it can plan and carry out software development tasks with user control.
Cogito Studio is a cross-platform desktop AI workspace built with Tauri, React, and Rust, offering multi-provider model access, MCP integration, workspace management, and local SQLite storage.
Cognee is an open-source framework aimed at simplifying data processing for large language models (LLMs) by creating knowledge graphs and data models, offering tools for information addition, knowledge creation, and similarity-based search
A Python CLI harness that lets coding agents access local tools such as Gmail, a browser, and files from their shell.
Context7 provides version-specific library documentation and code examples to agents through an MCP server.
ContextStream is an MCP server for shared project context and persistent agent memory, with semantic search, traceable sources, and scoped access.
Continue is an open-source autopilot plugin for VS Code and JetBrains, enhancing coding with LLMs through features like task and tab autocomplete, natural language edits, file generation, and customization options, available under the Apache 2.0 license
An OpenClaw-based multi-agent workforce framework with shared team memory, goal decomposition, fleet learning, task management, and approval workflows.
An open protocol for coordinating AI agent teams through shared Markdown task files and a chief-of-staff workflow.
A local-first memory tool for AI coding assistants that captures project context and carries it across sessions.
CorvinOS is a self-hosted agentic OS that connects local and cloud models to messaging platforms including Discord, Telegram, WhatsApp, Slack, and email.
