Business agents

A flexible Python factory for working with multiple Large Language Model (LLM) providers (OpenAI, Anthropic, Gemini, Llama) using a unified interface, with robust configuration and extensibility.

A Python framework for deploying AI agents as Slack bots

Model manager compatible with Ollama models through Ollama API for Quackamollie Telegram chat bot

Type-safe agent SDK wrapping pydantic-ai with Pydantic BaseModel I/O enforcement

QuantLET-agents - synchronous and asynchronous agents for discrete-event simulation. This is related to the distribution and simulation facets defined as part of the financial language SIGMA.

A lightweight, modular RAG system using ChromaDB

100% offline RAG storage and MCP server for querying local document knowledge bases

This is a local rag-mcp solution with chromadb using langchain and docling

RAG and Memory tools exposed via Model Context Protocol (MCP)

RAG in 3 lines. Auto-GraphRAG, auto-reranking, auto-streaming. No LangChain required.

3-level LLM cache (exact, semantic, partial) with real-time token cost tracking

RAG-powered document indexing and search for MCP (Model Context Protocol)

Training language models to perform agentic multi-hop search through reinforcement learning

RAG evaluation library — LLM-as-judge for hallucination detection, faithfulness, answer relevancy. Local or self-hosted. Alternative to ragas.

RAG-LAB is an open-source lighter, faster and cheaper RAG toolkit supported by Target Pilot, designed to transform the latest RAG concepts into stable and practical engineering tools. The project currently supports GraphRAG and HybridRAG.

Local-first RAG-lite CLI: condense docs into structured Markdown, then index/query with Chroma + hybrid search

Hybrid structure-aware retrieval — BM25 + embeddings + document graph expansion. Runs fully offline, no API key required.

Fast local RAG - search your documents with AI, no cloud needed

RawLLM – minimal orchestrator that exposes the raw power of LLMs

ReFeR: Improving Evaluation and Reasoning through Hierarchy of Models

ChromaDB VectorStore plugin for refinire-rag

Enterprise Multi-Tenant AI Companion Platform

Reminix agents for Anthropic - serve AI agents as REST APIs

Exporter for Anthropic Agent SDK telemetry to Respan

Respan instrumentation plugin for the Anthropic SDK

A Python library that meters Anthropic usage to Revenium.

Production-grade cross-vendor failover for LLM APIs

Multi-format bidirectional LLM proxy — translates between OpenAI Chat, OpenAI Responses, and Anthropic Messages

File storage utility implementation

Smart LLM request router — route prompts to the right model based on cost, speed, quality or complexity

Runtime budget, action, and audit authority for the OpenAI Agents SDK — enforce LLM cost limits, tool call caps, and audit trails before execution.

World's Most Comprehensive Secure Agentic AI Framework - 12 Security Foundations, Continual Learning, Multi-LLM Support

Sales Agent AI Agent Directory to Host All Sales Agent related AI Agents Services, Community, Reviews and More.

AI-powered multi-agent sales email generation MCP server using OpenAI Agents SDK

A Python SDK for interacting with the Agentforce Agents

Anthropic Claude Agent SDK integration for Sardis payments

A self-directed AI agent that grows through conversation

Microsoft AutoGen Python tool that gates KeeperHub workflow execution through SBO3L's policy boundary. Composable with sbo3l-sdk.

CrewAI tool wrapping SBO3L — gate every Crew action through SBO3L's policy boundary.

CrewAI Python tool that gates KeeperHub workflow execution through SBO3L's policy boundary. Composable with sbo3l-sdk.

LangChain Python tool wrapping SBO3L — gate every agent payment intent through SBO3L's policy boundary.

LangChain Python tool that gates KeeperHub workflow execution through SBO3L's policy boundary. Composable with sbo3l-sdk.

LangGraph adapter for SBO3L — drop a PolicyGuardNode between your plan and execute nodes to gate every action through SBO3L's policy boundary.

LlamaIndex tool wrapping SBO3L — gate every agent payment intent through SBO3L's policy boundary.

A comprehensive multi-provider LLM proxy library with unified interface

SCBE agent-bus: Python surface over the SCBE governed event runner. Routes AI/human/AI events through the harmonic-wall pipeline, wraps the workspace audit chain (formation/ingest/export/verify/import/lineage/report), and the trap-in-good-loops dispatch surface (free-only: offline echo + local Ollama).

Reveals the state of Schrodinger's famous llama and calls to mind the Mandela Effect.

searches through loads of files for simple searches that are next to each other, like clean, air

A Python client library for SeekGPT and other OpenAI-compatible LLM APIs.

SEF Agents — AI-powered guidance for the Synchronous Engineering Framework. Built on Model Context Protocol (MCP).

Universal LLM adapter service for Sekha AI - Multi-provider bridge supporting 100+ LLMs via LiteLLM

Semantic caching for LLM API calls - reduce costs with one decorator

AI-powered security agent — watches server logs, detects threats, and executes approved fixes via Sentinel dashboard

Common infrastructure for Shraga AI

Tiny IDs for big language models. Maps UUIDs to short, category-prefixed aliases optimized for LLM context windows.

Anthropic helper wrappers for Sigil Python SDK

Significance-threshold retrieval for RAG pipelines — stop injecting noise into your LLM context

Python SDK for SignalSwarm — build autonomous AI trading agents

A simple and easy-to-use LLM API Wrapper

Create a Python package.

Sinapsis templates for Anthropic Claude models.

24/7 AI agent that maximizes Claude usage via Slack interface

Zero-dependency LiteLLM-compatible facade for OpenAI, Anthropic, and OpenRouter

Provider-agnostic LLM router. Pick the cheapest capable model per prompt with rule-based scoring. Wraps LiteLLM for format conversion + streaming.

Advanced Legal Document Semantic Chunking System

A minimal Python library for interacting with various LLM providers

A Snakemake storage plugin that handles files available through Rucio.

Local-first AI agent with tools, memory, messaging gateway support, and optional provider extras.

Thin wrapper around posthog-python's AI integrations. Auto-tags LLM calls with project/service/env for unified cost dashboards.

Persistent identity and memory for any LLM agent — markdown-native, provider-agnostic

Anthropic client plugin for space-evals

SPL — A Declarative Language for Agentic LLM Workflow Orchestration

Runtime security for AI agents — detects jailbreak, prompt injection, and tool misuse from inside the agent.

Framework-agnostic agent observability & LLM tracing. Supports OpenAI, Anthropic, CrewAI, AutoGen, LangGraph, and OpenTelemetry.

Anthropic provider for Stache AI

A powerful Python ADK for building model agnostic AI agents

Ein thread-sicherer In-Memory Speicher, basierend auf Python-Dictionaries.

A simple synchronous way of accessing localStorage from your Streamlit app.

AI-powered threat modeling using the STRIDE methodology

Universal Python library for Structured Outputs with any LLM provider

Guaranteed structured output from any LLM — with automatic retries and validation

Enhanced CLI wrapper for Claude with beautiful JSON formatting

Enhanced LLM capabilities through test-time compute and search algorithms

Swarm Shield - TGSC

Swarmauri Anthropic LLM adapters from swarmauri_standard.

A tool for searching a specific word or phrase in a file.

SSH tunnel transport for forwarding Swarmauri traffic through bastions.

A Persistent ChromaDB based Vector Store

SWARMICA: Autonomous Physical Law Discovery System - From Classical Mechanics to Neural Operator Physics

Implementation and visualization of different swarm optimization algorithms.

Swarms - TGSC

Swarms - TGSC

A blazing-fast universal LLM gateway — call OpenAI, Anthropic, Gemini, Mistral & Ollama through one unified API.

OpenTelemetry Anthropic instrumentation

A complete terminal implementation of Anthropic's Claude.

A high-throughput and memory-efficient inference and serving engine for LLMs

HelixRAG: Retrieval-Augmented Generation with Graphiti-powered Knowledge Graphs

Drop-in Tessera integration for AutoGen (autogen_core / autogen_agentchat / autogen_ext). One line of config routes your AutoGen agents' LLM calls through Tessera's auto-route + auto-cache + auto-compress + auto-batch proxy. Free 60M tokens/mo. Production: 20% of measured savings.

Drop-in Tessera integration for CrewAI. One line of config routes your CrewAI agents' LLM calls through Tessera's auto-route + auto-cache + auto-compress + auto-batch proxy. Free 60M tokens/mo. Production: 20% of measured savings.

Drop-in Tessera integration for LangChain. One line of config routes your existing ChatOpenAI / ChatAnthropic / ChatMistralAI / ChatGroq / ChatCohere through Tessera's auto-route + auto-cache + auto-compress + auto-batch proxy.