SuperAPI AI Directory
Partner with us中文AI newsFavorites

AI developer platforms

3,640 results · Page 67 of 102

cordum

AI developer platforms

Cordum is an "action firewall" and Agent Control Plane for AI agents, providing a deterministic governance layer for autonomous AI agents. It can enforce policies and human approval before risky tool calls, shell commands, workflows, and production changes are executed, and leaves auditable evidence. Cordum adopts the Before/During/Across framework: before execution, define declarative policies, trigger safety kernel checks, or flag for human approval; during execution, monitor agent runs in real time, support step-level approvals and timeouts/circuit breaking; across agents, uniformly manage audit trails, capability routing, and agent pool health. The product also includes Cordum Edge—a compliance firewall for local AI agent actions such as Claude Code, which through command hooks denies risky actions before they run, requires approval for edits, and exports redacted evidence packages for each session. Cordum implements the open protocol CAP (Cordum Agent Protocol) for distributed agent governance, and is complementary to MCP. It provides a Go SDK (stable version) as well as Python and Node SDKs, including more than 30 integration packages (Slack, GitHub, AWS, Jira, Terraform, Datadog, PagerDuty, etc.). It is licensed under BUSL-1.1, allowing self-hosting and internal use, modification, and contribution back; it may not be offered as a competing hosted service, and converts to Apache 2.0 on January 1, 2029.

Read more

CorefluxMCPServer

AI developer platforms

Coreflux MQTT MCP Server is an enterprise-grade Model Context Protocol (MCP) server that provides secure, scalable access and automation capabilities to the Coreflux MQTT broker for MCP-compatible AI assistants such as Claude. It supports MQTT integration (including full TLS), the Coreflux API (models, actions, rules, routes), LOT (Language-of-Things) code generation via the Coreflux Copilot API, dynamic action discovery, and system health monitoring. The project also includes production-grade security, asynchronous processing, enhanced logging, configuration validation, and a complete testing framework, and provides Docker and Kubernetes deployment support, CI/CD pipelines, and an interactive installation assistant.

Read more

corellis

AI developer platforms

Corellis is an open-source system that extends a single OpenClaw AI assistant into a collaborative AI team (whose members are called "lobster"), used for task orchestration, shared knowledge, and collective memory. Each member runs in an independent Docker container, with private memory and sessions, while sharing the company knowledge base and searchable team memory. Core capabilities include: Teamind collective memory (builds an embedding index of Slack conversations, enabling retrieval of the basis for decisions across channels and history); a self-improvement mechanism (detects corrected content, records lessons, and propagates them to the whole team); GoalOps goal-driven operation (the controller breaks high-level goals into subgoals, assigns them, and lets members self-coordinate, including dependency tracking and human approval); a unified task board (supports Notion, Linear, GitHub Projects, or plain Markdown); generate a new member in 30 seconds; 17+ built-in skills; a confidence-routing workflow for coding agents; proactive task discovery; and fleet operations (rolling upgrades, configuration broadcast, health checks, and 24 other scripts). Prerequisites are that the host has OpenClaw installed and Docker available, and each member needs a Slack bot app. The repository claims continuous production operation since February 2026, with 28 members, 50,000+ indexed Slack messages, and 500+ self-corrections.

Read more

cortex-mem

AI developer platforms

Cortex Memory is an AI-native long-term memory framework built on Rust, providing a production-grade cognitive foundation for AI agents, embodied intelligence, and autonomous systems such as OpenClaw. It adopts a three-layer memory architecture of L0 summary → L1 overview → L2 details, combined with a virtual file system (cortex:// URI) and Qdrant vector semantic search, and can automatically extract, organize, and optimize memories from conversations. The framework provides multiple access methods such as SKILL, CLI, REST API, MCP protocol, and an insights dashboard, and supports multi-tenant isolation, session management, event-driven automation, incremental updates, and a memory cleanup mechanism based on the forgetting curve. Officially, it achieved a total score of 68.42% in the LoCoMo10 dataset evaluation and claims to save 11 times the tokens compared with OpenClaw+LanceDB.

Read more

cosmos

AI developer platforms

NVIDIA Cosmos is an open platform for physical AI, providing world models, datasets, and tools to help developers build applications such as robotics, autonomous driving, and intelligent infrastructure. Its current model family, Cosmos 3, is based on a unified Mixture-of-Transformers architecture and is an omnimodal world model that can see, reason, simulate, and act within a single model. The platform provides capabilities such as video generation, image and sound modalities, and supports multiple backends including Diffusers, Transformers, vLLM, vLLM-Omni, SGLang, TensorRT-LLM, and NIM. The models and source code are released under the OpenMDW-1.1 license. Before use, you must request access to nvidia/Cosmos-1.0-Guardrail and accept its conditions, and safety guardrails are enabled by default. Generated results may contain artifacts in long-duration, high-resolution, or physically complex scenarios, and safety-critical applications require additional validation.

Read more

CPPO

AI developer platforms

CPPO (Completion Pruning Policy Optimization) is a method for accelerating the training of reasoning models based on GRPO (Group Relative Policy Optimization). The project was released by lzhxmu on GitHub, and the paper has been accepted by NeurIPS 2025. Although GRPO is effective, it requires sampling multiple completions for each question, resulting in high training costs. CPPO significantly reduces the number of completions required for gradient computation and updates by pruning completions with lower absolute advantage, and introduces a dynamic completion allocation strategy that maximizes GPU utilization by incorporating additional questions. Experimental results show that, compared with the original GRPO, CPPO can achieve up to 8.32x speedup on GSM8K and 3.51x speedup on Math, while maintaining or even improving accuracy. The project provides a verl version and has open-sourced the relevant repository files.

Read more

creatify-mcp

AI developer platforms

creatify-mcp is an enterprise-grade MCP server for Creatify AI that exposes Creatify AI's video generation capabilities to AI assistants, chatbots, and automation tools. Built on the @tsavo/creatify-api-ts TypeScript client library, it turns complex video creation workflows into natural language interaction. The server provides 12 MCP tools (such as creating avatar videos with lip sync, URL-to-video, AI shorts, custom avatars, script generation, advanced lip sync with emotion control, etc.), along with 6 MCP resources (avatar list, voice list, templates, background music, remaining credits, etc.) and 5 workflow prompt templates. It also supports advanced features such as structured logging, progress tracking, and AI self-described help, and requires Node.js 18 or above and Creatify API credentials (Pro plan or higher).

Read more