Langchain agents

AG-UI FastAPI adapter for Agent-Spec (LangGraph/Wayflow)

Implementation of the AG-UI protocol for LangGraph.

Auto-instrument AI agent frameworks with runtime security. One line to govern LangChain, CrewAI, OpenAI, Anthropic — injection blocking, PII masking, action policy, audit trail. Zero code changes.

A Langgraph agent API server that implements Langgraph agent's web capabilities and can interact with chatbot

Static security analyzer for AI agents — prompt injection, tool input validation, MCP config auditing, secret detection. 53 rules mapped to OWASP Agentic Top 10.

Debug AI agent failures with minimal-config execution traces

Declarative, framework-agnostic AI agent orchestration via YAML

Chaos Monkey for AI agents

Carbon emissions tracking for LLM agent frameworks

Vendor-neutral MESI + optimistic-concurrency coordinator for multi-agent state — a stale write is denied or returned as a typed conflict, never silently applied; safety invariants model-checked in TLA+

Modular node architecture for LangGraph agents

Durable parallel conversations between LangChain agents.

Budget limits and cost guardrails for AI agent frameworks (CrewAI, AutoGen, LangGraph)

Framework-agnostic coverage testing and observability tool for LLM Agents.

Agent Debugger for LangChain/LangGraph

Chrome DevTools for AI Agents - Real-time debugging, pause, inspect, and step through your AI agent execution

Agentic Context Engineering (ACE) middleware for LangChain — self-improving playbooks from the ICLR 2026 paper by Zhang et al.

Production-ready evaluation framework for AI agents — 58 metrics (25 native + 33 Harness Config) across 7 evaluation gates: goal achievement, behavioral integrity, reliability, performance, security, multi-agent coordination, and observability

A Circuit Breaker for AI Agents - Fail Safe by Default

Turn plain-English requirements into production-ready multi-agent AI projects (CrewAI, LangGraph, WatsonX Orchestrate).

Action-level governance for AI agents -- control what they DO, not what they SAY

Harness as a Service — production-grade multi-agent harness with LLM routing, paged context, hierarchical tracing, safety, and self-improvement

Adaptive threat intelligence for AI agent security — semantic memory, multi-turn escalation, output scanning, rate limiting, and prompt hardening.

A GenAI project built with LangChain and modern Python tools

Detect and debug loops in AI agent execution

Three-layer persistent memory system (Markdown + ChromaDB vectors + NetworkX graph) for AI agents

A reusable memory layer for SAP agentic workflows

A comprehensive monitoring solution for AI agent frameworks including Langchain, CrewAI, and Agno. AgentMont provides enhanced metrics and deep observability for production AI agent applications.

Nexus is an autonomous CLI coding agent powered by LangGraph and MCP. It plans complex tasks, persists context via SQLite, and securely orchestrates tools. Features specialized Architect/Code modes, real-time metrics, and human-in-the-loop safety for production workflows.

Lightweight Python SDK for Agent Observability Tracing — instruments multi-agent AI workflows

Agent observability with cost tracking and compliance audit trails

LangChain integration for Agent Observability - structured logging, cost tracking, and compliance for AI agents

Reusable AI agent workflow patterns using LangGraph and LangChain

LLM-agent working memory as a session-scoped fact graph: a @pin decorator extracts facts from tool returns, ready-made graph-read tools let the LLM navigate them.

A lightweight production ready agentic framework to build your agents

Agent Policy Layer - Portable, composable policies for AI agents

Role-Based Access Control for AI Agents with ML-Powered Anomaly Detection

Structured session checkpointing for AI agents — survive context limits, cost overruns, and session death

Production-grade self-correcting AI agent platform with sandboxed execution

In-process SDK runtime for agent-search

In-process SDK runtime for agent-search

Enterprise Security Monitoring SDK for AI Agents - Secure any AI agent in just 3 lines of code with real-time threat detection, behavioral analysis, and separate logging and threat reporting for comprehensive security monitoring

Complete SDK for integrating Agent Skills into any Python agent framework

Agent observability: trace any AI agent and store runs in MongoDB (and more)

Production-grade resilience for AI agent tool calls: retries, fallbacks, circuit breakers, and validation

The Tooling Layer - Transform agent decisions into actions via unified tool abstractions

MCP server that diagnoses why your agent behaved the way it did, and how to fix it

LangChain integration for TrustAgents - protected document loaders, retrievers, and threat scanning

Batteries-included framework for building automation-focused AI agents with observability

Connect AI agents across any network — no public IP needed. P2P encrypted, NAT-traversing, zero-config on LAN.

Runtime compliance evidence for AI agents — one-line SDK, tamper-proof audit trail, multi-framework attestation

Huawei Cloud AgentArts SDK - Build, deploy and manage AI agents with cloud capabilities

Behavioral testing framework for AI agents — pytest for AI agents

Python SDK for AgentAuth - Authorization layer for AI agent purchases with billing support

Deploy, observe, and auto-heal your AI agents

Management & Observability SDK for AI Agents

Production monitoring for AI agents. Heartbeat monitoring, cost tracking, failure detection.

AgentBill MCP server. Add spend controls and billing to any AI agent in 3 lines.

LangChain callback handler for automatic usage tracking and billing with AgentBill

LangChain callback handler for automatic usage tracking and billing with AgentBill

Preflight spend control for AI agents. Block runaway loops before they start.

A flight recorder for AI agents – record every decision, tool call, and failure

Python SDK for AgentBouncr — Governance for AI Agents

Orchestrate LLMs in a multi agent system using Langchain and/or Llama index. Manage agent interactions, task routing, and knowledge sharing

Collection of LangChain-specific classes and functions used with the Couchbase Agent Catalog project.

Collection of LangGraph-specific classes and functions used with the Couchbase Agent Catalog project.

AgentCard v1.0 adapters for LangChain, CrewAI, and AutoGen

Agent Center - A Python project built with LangChain for managing AI agents

like langchain but not awful

One decorator to make any AI agent reliable. Loop detection, auto-repair, output validation, budget control.

Visual debugger for AI agents. See every step, every decision, every failure.

AgentClaw turns one-sentence ideas into reusable Claw capabilities with declarative workflows, computer/browser/code/file control, MCP, Skills, memory, knowledge bases, tracing, scheduling, and API/MCP publishing.

Never let your AI agent fail again — automatic fallback to AgentClear's marketplace of 60+ API services.

Agent quality analysis and repair SDK for OpenTelemetry traces

Track LLM costs across OpenAI, Anthropic, Gemini, LangChain, and 3500+ models with zero code changes

Institutional control layer for AI agent actions — authority, policy, risk, and audit before execution.

Agent Development Kit for building intelligent agents with LangGraph and MCP integration, Support Agent Async in jupyter notebook/IPython

Sentry for AI Agents — one-line observability with local SQLite persistence

Coordination layer for AI scheduling agents — race-free multi-agent booking with priority ranking and an audit log.

LangChain tools for AgentDraft — let LangChain, LangGraph, CrewAI, and AutoGen agents book calendars through the coordination layer without colliding.

Kingsoft Cloud Agent Engine SDK alias package for ksadk

Orchestrate AI agents in perfect harmony - A comprehensive Python framework for building, testing, and orchestrating multi-agent AI systems

Agenter — Backend-agnostic SDK for autonomous coding agents supporting Claude, Codex, Anthropic, and AWS Bedrock with streaming, budget controls, security validation, and LangGraph/PydanticAI adapters.

The open source SDK for AI agents Identity.

MCP server for fetching web URLs with token estimation, smart caching, and intelligent routing. Built for AI agents.

Multi-agent orchestration platform over MCP servers

Runtime protection and security monitoring for AI agents — The CrowdStrike for AI Agents

Intelligent LLM agent cost optimization runtime — per-run budget enforcement, semantic caching, model routing across 15 providers

Chaos engineering for AI agents — inject realistic production failures (tool timeouts, malformed responses, cost spirals, prompt injection) and find out what breaks before your users do.

E2E behavioral testing for AI agents — grounded in 24 research papers. Playwright for LLM agents.

Context-aware trust authorization for agentic AI systems

Action-level firewall for AI agents — intercepts tool calls before execution.

The security gateway for AI agents — auth, rate limiting, and policy enforcement in one line.

Compliance-as-code middleware for agentic AI workflows.

Zero-infrastructure AI agent tracing for Grafana + Loki

AgentGraph bridge for LangChain — register agents and graphs with the AgentGraph trust network

Deadlock prevention for multi-AI-agent systems using the Banker's Algorithm. C++ core, Python bindings, LangGraph integration.

Production-grade fault tolerance for AI agentsidempotency, loop detection, fallback chains, async support, health monitoring, and budget enforcement for LangChain, AutoGen, CrewAI, and any LLM pipeline

Real-time cost observability and guardrails for AI agents

Runtime security firewall for LangChain agents — intercepts tool calls, enforces YAML policy, logs to SQLite.