Search

Single-Input-Reasoning: one LLM call, full action graph execution with evolutionary memory

Design review tool for prototypes. Annotate UI elements, generate agent prompts, paste into Cursor/Claude Code.

LLM security layer — prompt injection detection, coordination injection defense

Multi-provider AI agent CLI supporting Ollama, Bedrock, OpenRouter, Gemini, and xAI

Framework-agnostic tools for Dhruva Agent Identity (ERC-8004) — EIP-712 registration signing, EIP-191 identity proofs, and on-chain status lookup. Works with Mastra, LangChain, Vercel AI SDK, or plain function calling.

Lounge integration for BPS AI agents — channels, beliefs, hypothesis lifecycle

Enforcement and containment for BPS AI agents

Persistent knowledge traces for AI agents — structured knowledge graphs that survive session restarts

Query your codebase — structural SQLite index for AI agents

Open-source hooks, policies, and project visualization for Claude Code & Agents SDK

BSC AI Agent Token Deployer — Launch AI agents on BNB Chain via Bouncher platform

A TypeScript framework conversational AI agents with AGIML plugin for LLM<-generated hypermedia and cross-modal content generation

X-ray any codebase — for humans and AI agents

Record what your AI agent is allowed to do

ClawsBench: Evaluating Capability and Safety of LLM Productivity Agents in Simulated Workspaces

Google Ads CLI & Skills for AI agents (and humans)

A GenAI project built with LangChain and modern Python tools

Thin LangChain adapter for PFC execution-boundary decisions

Agentic AI banking assistant with LangGraph multi-agent workflows, CockroachDB vector search (langchain-cockroachdb), durable checkpointing, receipt OCR, fraud detection, and multi-provider support (OpenAI, AWS Bedrock, IBM watsonx, Google Gemini)

Launch Claude Code agents on GitHub repos with isolated workspaces and optional Docker dev environments