Search

Manifest-driven managed-KMS orchestrator: provision per-identity Cloud-KMS HSM signing keys + per-key IAM, resolve each agent's Smart Agent (agent-naming), derive + verify the EVM delegate address, and push the minimal runtime secrets to deploy targets wi

A logical reasoner that uses a knowledge graph as a world model and the IKL logic DSL to beat dense-embedding/RAG precision+recall: ingest documents into a SQLite KG, query/forecast/counterfactual via IKL compiled to SQL, and return D3-visualisable graphs + grounded LLM interpretations with honest refusal. Local developer tool; the only AWS dependency is Bedrock InvokeModel for the Strands agent. Bundles hyper-kg + hyper-gliner.

Cross-language AI Agent orchestration - Python FastAPI LLM core + Java Spring Boot admin.

Cognitive memory for AI agents. Bitemporal, multi-tenant Postgres + pgvector. Hybrid recall (BM25 + vectors + graph) with BYO LLM. Use as a library, HTTP API, or MCP server.

REST API server for AgenticMail — email, SMS, and phone call-control endpoints for AI agents

OpenClaw plugin for AgenticMail — email, SMS, and phone call-control for OpenClaw agents

Autonomous orchestrator skill for Claude Code, OpenClaude, Copilot, Cursor, and Kilo. Takes a goal, discovers available skills/MCP/CLI tools, decomposes into phases, maps to skills, executes with monitoring, and verifies until done.

A lightweight toolkit for teams adopting AI coding agents, structured PR review, and business automation workflows.

Universal AI agent orchestration kit for Cursor, Claude Code, and Amp Code — spec-driven pipeline with OpenSpec integration

uniner-cli — RPA automation CLI: browser automation (Playwright/CDP), Excel, OCR, desktop/SAP, crypto/HTTP/email tools. Auto-installs a Claude Code skill on install.

QQ Bot adapter for Chat SDK

A State-Aware Rollback and Trajectory-Replanning Framework for Autonomous LLM Agents

Depot — 面向代码生成 Agent 的按需依赖解析系统

Collective knowledge store for AI agents — publish facts at runtime, query shared learning

AgentRelay Secure Memory Persistence and Recall integrations for AI frameworks.

Python SDK for SeaArt agent-gateway APIs

Lightweight provider-agnostic agentic coding backend (CLI + server) for the Euron VS Code extension.

Gemini 3.1 Flash Image, a.k.a. "Nano Banana 2," is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines advanced...

Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...

A lightweight guardrails framework for AI agents that supports multiple languages, primarily Arabic and its dialects, for safety and PII governance.