Search

LangChain toolkit for AgentSats — Tokenized AI compute and identity on Teranodex

An open-source modular AI agent framework. Plug in IRC, Discord, Telegram, web — power it with Claude or any LLM.

High-performance acceleration for CrewAI - 2-5x faster memory, tools, and task execution with zero code changes

3D AI agent platform for the browser. Load any GLB/glTF avatar, give it an LLM brain, and embed it as a web component.

Opinionated Pi package with web search, review workflows, sandboxing, memory, usage reporting, skills, and a theme

Expo/React Native adapter for @equationalapplications/core-llm-wiki.

Structured LLM task runner with outcome routing via file signals

Vercel AI SDK provider that routes through Perplexity's /v1/agent endpoint, giving access to Anthropic, OpenAI, Google, xAI, NVIDIA, and Sonar models with one Perplexity API key.

SciTeX GenAI — modality-organised generative-AI provider abstraction (LLM, agents, image/audio/video stubs)

Transpile a neutral agent configuration into Claude Code, Codex CLI, and other agent-specific formats — and back again.

Pi provider bridge that runs Claude Code through the Claude Agent SDK, with opt-in forwarding for Pi prompt context.

Multi-bot Lark/Feishu bridge for OpenClaw, with per-bot model routing and isolated sessions

Pine Labs Agent Toolkit — Pine Labs payment APIs as tools for AI agent frameworks (OpenAI, LangChain, Pydantic AI, CrewAI, Anthropic Claude).

OpenAaaS: science agent network — bring AI to your data, not your data to AI. MCP protocol, local execution, Docker sandbox, zero-config Rust nodes.

Antarraksha AI Agent Enforcement SDK for LangChain

Antarraksha AI Agent Enforcement SDK for Crewai

Antarraksha AI Agent Enforcement SDK for Openai Agents

Dynamic prompt management and configuration library for LLM applications. Powerful, lazy-loading, and supports Jinja2 templates and Pydantic schemas.

Self-healing engine for LLM APIs - Automatic fault diagnosis and 4-level cascade recovery

Agent Token Manager (agent-atm) - A lightweight, privacy-first LLM token usage metering & quota capping SDK.