Python agents

LangChain vector store for polign_db

Sub-millisecond PII detection and prompt injection firewall for LangChain

Per-turn skill routing for LangChain deepagents: a pluggable judge (Jev included, or your own) loads only the SKILL.md skills each turn needs, keeping a catalog of hundreds out of the prompt.

LangChain tools and Python client for the ThorData SERP API

LangChain tools for Twelve Data market data

A LangChain integration for TypeSafe classifiers

LangChain document loader and agent tool for the Velrim document-extraction API: extraction against a JSON Schema you supply, with per-field state (present, null, missing), a per-field confidence score, and source anchors (page + bounding box).

A pure-Python BM25 (lexical) retriever for LangChain, powered by Whoosh.

Runtime sandbox integration for Deep Agents

A LangChain Tool that pays per-request for SAGG LLM chat completions via the x402 protocol - no API key needed.

LangChain tools for xdataapi.io: read-only public X (Twitter) profiles, tweets, threads, followers and search.

Zambo's 153 MCP tools as LangChain StructuredTools: a verifiable AER-1 receipt for every call, no API key

Use ACP-compatible agents as first-class LangGraph nodes.

GridGain checkpointer, store and node cache for LangGraph — short-term thread state, long-term cross-thread memory, and node-level caching.

LangGraph checkpoint savers on plain Redis (sync + async) - no RedisJSON / RediSearch modules required, works on Redis 5+

Policy enforcement and guardrails for LangGraph AI agents

Jev-first routing for LangGraph: keep your LLM router as the fallback, let TypeSafe's Jev take the confident decisions.

Find LangGraph wiring bugs before they become a runtime KeyError.

Long-term memory engine for LangGraph over any BaseStore — LLM fact extraction, consolidation, and recall ranked by semantic similarity, recency and importance (a maintained alternative to LangMem)

SingleStore checkpoint saver and store for LangGraph

MCP server + Claude skill for building LangGraph projects by editing a structured YAML spec instead of regenerating Python each turn

Shared core for LangGraph long-term-memory (BaseStore) backends — implement a store with four small primitives

Azure CosmosDB long-term-memory store (BaseStore) for LangGraph — namespaced key/value memory with filters, list_namespaces and native semantic (Cosmos DB vector) search

Google Firestore long-term-memory store (BaseStore) for LangGraph — namespaced key/value memory with filters, list_namespaces and native semantic (Firestore vector) search

PostgreSQL long-term-memory store (BaseStore) for LangGraph — namespaced key/value memory with filters, list_namespaces and native semantic (pgvector) search

The LangGraph side of agent-wait: ask() to declare a question at the interrupt site, an adapter that reads what a thread is parked on, and helpers for the host's start/resume routing.

A provider-neutral explainability layer for LangGraph applications.

libCellML a library for the creation, printing, parsing, and manipulation of CellML models.

Strongly typed Python SDK for Lingya Agents OpenAPI

Declarative synchronization CLI for LiteLLM models, credentials, access groups and virtual keys.

A Textual TUI for managing LiteLLM proxy models

Standalone LLM cost estimation: model pricing data + token cost math, extracted from LiteLLM with zero litellm dependency.

Serve Claude Max, ChatGPT Plus/Codex and Google Antigravity subscriptions as OpenAI-compatible models through a LiteLLM proxy

Client SDK for Liviate's RAG stack: ingest, embed, retrieve, rerank, and (optionally) generate.

LlamaIndex ToolSpec and Reader data connector for Adam Network

Sub-millisecond PII detection and prompt injection firewall for LlamaIndex

Drop-in LlamaIndex reranker powered by TypeSafe Jev (typed 0–3 scores)

EnConvert reader for LlamaIndex: perceive URLs or ingest a whole site into Documents, every read scored.

LlamaIndex reader for the Velrim document-extraction API. Extract documents against a JSON Schema you supply and get back a Document carrying the extracted object, per-field state (present, null, missing), a per-field confidence score, and source anchors.

A pure-Python BM25 (lexical) retriever for LlamaIndex, powered by Whoosh.

Drop-in LlamaIndex selector powered by TypeSafe Jev (typed tool / query-engine choice)

LlamaIndex tool spec that lets agents discover APIs, MCP servers and CLIs through the Agent Nexus registry

LlamaIndex tool spec for the Council of AI GSPC measurement board (wraps csoai-gspc).

llama-index tools feedmyagent integration

Thordata SERP tools for LlamaIndex agents.

LlamaIndex tool spec for xdataapi.io: read-only public X (Twitter) profiles, tweets, threads, followers and search.

LlamaIndex integration for Infino — vector, BM25, hybrid (RRF), and SQL retrieval over one engine on object storage.

LlamaIndex vector store for polign_db

Find, size, install and verify open-weight LLMs for llama.cpp on your own machine.

Official Python SDK for the HyBit Vector Database

Universal, provider-agnostic local LLM response analyzer with SQLite storage and a local dashboard.

Official DeepSeek API package for llm-api-adapter

Kimi / Moonshot package for llm-api-adapter

Qwen Model Studio package for llm-api-adapter

Official Z.ai GLM API package for llm-api-adapter

llm plugin for APIMaster and other OpenAI-compatible gateways, including image and video generation

ChatGPT Codex subscription provider for llm-async

One transform spec, compiled to Python/Rust/TypeScript, translating LLM requests between provider formats.

Provider-agnostic LLM discovery, stability testing and AIPerf benchmarking

Lightweight semantic caching for LLM applications, backed by Redis.

LLM cost attribution per feature — track which parts of your product are spending your AI budget

Structured probabilistic decision inference for local causal language models using direct candidate scoring.

Núcleo versionado del que dependen 52 proyectos en 52 semanas: un solo sistema acumulativo.

A lightweight, offline Python library for scoring LLM response quality. This project is made under the INFERENCE Lab engineering cohort 01.

Lightweight diagnostic linter for LLM extractions (catches dropped braces, markdown leaks, and hallucinations).

Self-hosted AI gateway for Mac — one OpenAI-compatible LAN endpoint serving local MLX models with cloud API key fallback.

Encode data as token-efficient, LLM-friendly strings

A local web UI for managing LLM API keys

OpenAI-compatible HTML and document to Markdown conversion helpers

A simple transparent MITM proxy for LLM APIs with a live Web UI

A Python library to visualize LLM perplexity metrics in interactive graphs

Generate tested terminal LLM chatbot projects for Groq, Google Gemini, OpenAI, and Anthropic Claude

OpenAI-compatible LLM client with multi-provider fallback.

Additional files for the Hanzo AI proxy runtime. Kept separate so the main hanzo-llm package stays small.

Provider-neutral Python instrumentation, portable execution artifacts, and an MCP interface for the Refract execution engine.

An LLM development tool like requests.

MCP server for LLM safety checks (prompt injection, PII detection, sanitization)

LLM-based semantic chunking library for RAG pipelines

Tag LLM spend the way cloud spend is tagged, with calibrated decision models, and export it as FOCUS 1.4

Use TypeSafe classification and scoring models with LLM

LLM plugin for models served by Unsloth Studio

Generic LLM usage and observability framework

Placeholder — reserved for upcoming project.

Any chat model, any engine (SGLang, vLLM, transformers, MLX) as a Jev-compatible probability decision service

An embeddable bash-compatible shell that minimizes its own output, for LLM agents

Мы предоставляем Вам удобную возможность - развернуть модель на облаке или на компьютере локально и использовать ее с другой точки мира! Работает это просто - сначала Вызапускаете модель на любом железе, получаете ключ доступа (Local_CreateCode()) и сопряжаете по нему устройства. Далее - работайте по документации (https://llmconstructor-pylibrary.onrender.com/docs).

Standalone PII detection and masking guardrails for text pipelines (PIIGuard).

Compatibility forwarder for llmgraph-mcp (llmgraph.in)

Official Model Context Protocol (MCP) server for LLMGRAPH semantic code intelligence

Typed, composable agent building blocks with explicit budgets and outcomes

Context assembly and memory for llmgrid

Typed contracts for llmgrid composable agent capabilities

Composition runtime and agent recipes for llmgrid

Model adapters for llmgrid

Retrieval-augmented generation for llmgrid

Typed tool bindings and dispatch for llmgrid

Official Python SDK & CLI for LLMPodium — 700+ AI models leaderboard, LMSYS Arena Elo, benchmarks, and API pricing.

Inspired by Jev. Turn LLMs into decision engines—score choices, skip the chat.

Reserved name for the Loaded Llama (loa-lla) beastie — Data Boar beastiary. Placeholder; implementation forthcoming.

Local chat UI for OpenAI-compatible and GigaChat models with persistent history