Business agents

The circuit breaker for AI agents. Detect runaway loops and cost spikes in real time.

AI governance SDK — intercept, audit, and control AI agent tool calls. Add human-in-the-loop approval, kill switches, and a full audit trail to any AI agent.

Stops LLM agents from silently guessing what they don't know

OpenClaw plugin that lets any agent drive LangGraph workflows from inside a conversation thread with proactive event wake-back.

AG-UI lifecycle and concurrency checker for LangGraph agents

Zod contracts for the self-hosted CopilotKit and LangGraph thread platform

Agent orchestration mock harness for kiwa — LangGraph-style state machine (StateGraph.addNode + addEdge + compile → invoke / stream) and OpenAI Assistants v2 (Assistant + Thread + Message + Run + run.poll) unified under one API. Ships stateful conversatio

Headless agent-workflow model (Handoff 12 A-1): the JSON schema for a governed AI-agent sub-workflow — exactly three node types (llm/tool/decision) plus decorators (memory/planner/errorBoundary) — a versioned id@semver reference parser, and graph validati

Platform-agnostic JSX channel engine for CopilotKit (createChannel, Thread, PlatformAdapter, ActionStore).

Governed-knowledge retrieval + injection for LLM agents -- concepts, playbook entries, three-scope shadow merge, and before_model middleware

AG-UI integration for Claude Managed Agents (Anthropic hosted agent sessions)

Keep agents at capability parity across harnesses (creds, E2E tooling) from one manifest

Record-and-replay for agent decision graphs: reproduce a prod agent failure as a committed regression test — and re-run your fix without live LLM calls.

A local zero-token agent status API with OpenAI and Anthropic compatible streaming

Unified pgvector-backed CLI for agent notes (breadcrumbs, memories, reflections) shared across the sf2 constellation

Statistical regression testing for LLM agents. Get a p-value on whether behavior actually shifted between versions, not just whether one run looked different. Apache 2.0, self-hostable, no SaaS dependency -- a Promptfoo alternative for the statistical testing gap threshold-based eval tools don't cover.

A Python framework for managing reusable AI skills throughout their lifecycle.

Agent-ready command-line interface for Close CRM — set up leads, keep contacts and notes current, track tasks and opportunities, and search across all of it. Installs the `close` command.

Protocol bridge for OpenAI Responses, Chat Completions, and Anthropic Messages clients.

Gradient descent, but the parameters are agents — a parallel, asynchronous framework for self-evolving agents (skills, prompts, harnesses)

Read-only Threads retrieval through authenticated, single-target CLI primitives

Detect and kill infinite AI agent loops before they burn your API budget.

Anthropic helper wrappers for the Grafana Agent Observability Python SDK

AgentSecure SDK — LLM DLP proxy for Python

Provider package apache-airflow-providers-anthropic for Apache Airflow

The ergonomic, standalone Python SDK for agentic payments: embed payments in your product (or give your AI agent a payment tool) under a signed, capped, payee-scoped contract over HTTP. Three nouns — agent, contract, payment.

LLM agent library with tool use, dynamic tool generation, and software evolution capabilities

LangChain tool: scan Base contracts via BaseSentinel (HTTP 402 + USDC tx-hash proof).

Salesforce AgentForce as a traversable knowledge graph — 40 nodes, Einstein Trust Layer, Resolution Criteria, 2-dollar-per-resolution billing path. 11x fewer tokens than RAG. MCP-native.

Scaffold a FastAPI + Claude API + Railway + Netlify/Vercel project in 30 seconds.

Convert Anthropic Claude exports into an organized local knowledge base.

Verifiable multi-agent consensus for Claude. The coordination layer frameworks punted on.

Wrap your Anthropic / OpenAI Python client. Every tool call is inspected by Clavenar before it runs.

Tarification, comptage de tokens et affichage LLM partagés du parc

LLM-powered multi-platform bot framework (Telegram + Discord; OpenAI + Anthropic)

Python base for DLLM-compatible conversational applications.

A Google Drive Container storage and synchronization manager with persistent OAuth, deduplication, and verification.

Use Eden AI with Haystack to build AI applications with 500+ AI models through one unified, OpenAI-compatible API.

A Python-first Agentic AI Framework — provider-agnostic, async-first, middleware-driven

Claude on Genkit

A glass-box, minimal library for building LLM agents — modern techniques as opt-in primitives, no hidden control flow.

Google-OAuth-gated LLM gateway: verify a Google ID token, then run a Gemini (Vertex AI) completion for the verified caller.

Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith tracing.

Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith tracing.

Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith tracing.

Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith tracing.

Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith tracing.

Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith tracing.

Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith tracing.

Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith tracing.

Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith tracing.

Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith tracing.

Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith tracing.

Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith tracing.

Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith tracing.

Proxy Gemini (Vertex AI) completions wrapped in OpenTelemetry trace spans; returns the answer plus the trace/span id.

Ontology-driven knowledge-extraction pipeline: paragraphs to a typed, provenance-anchored Knowledge Artifact Graph.

Central task registry and deterministic three-agent orchestrator for doctor-agent, repair-agent and validator-agent.

LLM agent policy for Inspect Robots: frontier LLMs (Claude, GPT, anything OpenAI-compatible) drive any registered embodiment through tool calls.

AxioRank middleware for LangChain agents: govern every tool call and model turn through one Zero-Trust security gateway.

An integration package connecting Bidda source-verified compliance intelligence to LangChain

Make Anthropic Model Context Protocol (MCP) tools compatible with LangChain and LangGraph agents.

LangChain tools for Relm - the CRM for LLMs and AI agents

LangGraph checkpointer backed by inspeximus: durable thread state with queryable value history and receipted erasure.

Anthropic Claude agent handler for LaunchDarkly AI SDK

Anthropic Claude messages handler for LaunchDarkly AI SDK

Legal AI agents framework — extension of smolagents with structured, jurisdiction-agnostic legal reasoning (French law example included)

Free-first LLM routing for Python: local Ollama -> OpenRouter free models -> paid Anthropic API, with automatic fallback and a savings ledger.

A tiny, readable circuit breaker for LLM calls: hard budget caps that fail over to a free local model instead of raising or overspending.

Multi-format LLM API compliance testing tool — validates endpoints against OpenAI Chat, Open Responses, Anthropic, and Google GenAI specs.

Fit chat history into any model's context window: token estimation, sliding-window packing with a running summary, and overflow detection. Zero dependencies, no AI inside.

Composable pre-call and post-call hooks for LLM API calls: pricing, budgets, cost caps, rate limits, event log, observability.

The pre-merge check for LLM model, prompt, schema, and provider changes

A GitHub Action and CLI that detects risky changes to LLM prompts and AI configuration before they ship to production

Resilient cascading LLM inference across multiple providers with failover, circuit breaking, and retry cooldowns

Client-side rate limiting for the Claude API. Never sees your API key.

Local smoke tests for live LLM models, latency, and cost

Per-query token ledger for LLM pipelines: record what the API reports, answer with one GROUP BY. Zero dependencies, dashboard included.

Lightweight terminal tool to check remaining credits / quota across LLM providers. Zero dependencies.

LLM plugin for ZenMux.ai - OpenAI Chat Completions + Anthropic Messages API

Unified interface to call OpenAI and Anthropic-compatible LLM APIs from Python

AIGP governance adapter for anthropic

Durable Anthropic Messages adapter for the MemoFlow Python SDK

Bit-exact Byzantine-fault-tolerant state layer for federated learning and edge/defence swarms. Three layers — OR-Set CRDT (L1), an epistemic drift + human-in-the-loop layer (L2), and ACFA Q16.16 multi-Krum + G-Set (L3) — keep heterogeneous nodes byte-identical; one prompt-injected or equivocating node can't fork, poison, or move the agreed state. Every write is signed, attributable, and exactly replayable. Architected for large swarms; bit-exact by construction.

This module allows to base replenishments quantities (on stock locations) on average daily sales

OpenTelemetry Anthropic instrumentation

Orqis SDK - one line to stream AI agent traces to Orqis self-healing ops

Unified Agent Core — declarative agent manifests, pluggable registries, and interfaces for the AgentForge harness.

Read-only staleness/orphan/duplicate/retrievability checks for a single pgvector, Qdrant, or Chroma index.

Bi-temporal RAG platform: cited, temporally-correct answers plus system-time replay. Self-hostable memory and audit layer for AI agents.

Build semantic search, multi-provider question answering, and REST APIs over your documents in a few lines of Python.

Sentinel AI — client SDK for AI agent governance & identity. Sign agent actions with Ed25519 and enforce them through the Sentinel authorization gateway. Private beta: [email protected]

Anthropomorphic psychology engine built on SPL Pure Core V8.0 — deterministic emotion, trauma, memory, trust, and defense mechanisms.

Swap between LLM providers (Groq, OpenAI, Anthropic) through one interface, with automatic fallback and optional schema validation.

TAPM v2 hook for Anthropic (in-process library instrumentation)

TechTide Swarm 357 — layered orchestration, durable memory bridge, and observability hooks.

Time-aware semantic LLM cache — automatically invalidates stale AI answers

THEMIS — Retrieval-grounded LLM for Indian statutory law (BNS, BNSS, BSA, IPC, RTI)

Library to systematically track and evaluate LLM based applications.

Client SDK for Warden — build and sign canonical Warden delegation tokens, and route agent frameworks through the Warden MCP proxy.