This is an early release preview. You may encounter bugs.

Catalogue

Submit a tool

Frameworks, tools, apps, and blueprints for agent builders — each scored on real GitHub credibility, each with a credibility-gated forum.

Tagged #python ×
Tool

Agenta

Agenta-AI

Evaluate and compare different agent configurations side by side.

B
Tool

aider

Aider-AI

Terminal-based AI pair programming, git-aware and ready in your shell.

C
Framework

BeeAI

i-am-bee

Cross-framework agent orchestration with the Agent Communication Protocol

A
Tool

BrainDB

dimknaf

Postgres+pgvector long-term memory (typed entities, graph, decay) with a native Hermes plugin.

C
Tool

Browser Use

browser-use

Control browsers programmatically with LLM agents through a high-level, LLM-friendly API.

A
Framework

Camel

camel-ai

Customizable multi-agent systems for role-playing, simulations, and data generation

A
Tool

Chatterbox

resemble-ai

State-of-the-art 0.5B zero-shot text-to-speech model for expressive dialogue.

C
Tool

ChatTTS

2noise

Conversational text-to-speech for dialogue scenarios, in English and Chinese.

C
Tool

CogVLM2

THUDM

General VQA, document Q&A, and GUI understanding with high-resolution inputs

D
Tool

Conversational Speech Model (Sesame)

SesameAILabs

Multimodal model generating human-like conversational speech with autoregressive transformers.

D
Tool

Docling

docling-project

Document conversion with layout analysis and table structure recognition

A
Tool

Giskard

Giskard-AI

Detect performance, bias, and security issues in AI applications.

A
Tool

GPT Researcher

assafelovic

Autonomous online research agent that scrapes, summarizes, and exports findings to PDF.

A
Tool

Hermes Client

lotsoftick

Web/PWA that wraps the local `hermes chat` CLI over SSE; multi-profile, spend caps, channel binding.

D
Tool

Hermes HUD

joeynyc

Open-source TUI monitor for Hermes (context, skills, agent activity).

C
Tool

hermes-dynamic-workflows

lingjiuu

Brings Claude-Code-style dynamic workflows to Hermes — sandboxed Python orchestrating up to 1000 subagents.

D
Framework

LangChain

langchain-ai

Chainable modules with extensive integrations, memory, and tool support

A
Framework

Langflow

logspace-ai

Drag-and-drop visual builder for agents, integrating LangChain and LlamaIndex

A
Tool

LangMem

langchain-ai

Integrated long-term memory management for developers building on LangChain and LangGraph.

C
Tool

Mnemosyne

AxDSan

Local SQLite memory provider for Hermes — sub-ms recall, tiny-LLM consolidation. Community “best balance” pick.

A
Tool

model-router

open-world-project

Cost-aware per-turn routing plugin for Hermes (5 tiers, auto-escalation, manual pins).

D
Tool

Molmo

allenai

Open-ended question answering and document reading, excelling at dense text like charts and forms

D
Tool

mPLUG-DocOwl2

X-PLUG

Multi-page document QA without OCR dependency via a high-resolution DocCompressor

D
Framework

OpenAI Agents SDK

openai

Lightweight agent framework with minimal abstractions and flexibility across LLM providers

A+
Tool

OpenLLMetry

traceloop

Observability for LLM applications using OpenTelemetry.

A
Tool

PaddleOCR

PaddlePaddle

Comprehensive OCR pipeline for multilingual tasks requiring high accuracy

A
Tool

Pipecat

pipecat-ai

Open-source Python framework for building real-time voice and multimodal conversational agents.

A
Tool

Qwen2.5-VL

QwenLM

Vision-language model for complex document QA, structured data extraction, and long-context processing

C
Tool

screenshot-to-code

abi

Turn screenshots into clean HTML, Tailwind, React, or Vue code for fast UI prototyping.

C
Framework

uAgents

fetchai

Lightweight Python framework for building and connecting decentralized agents.

C
Tool

Video Report Nemotron

AetherX-Technologies

Hermes skill turning a video into a structured Markdown/HTML/PDF report (local ASR fallback + OCR).

D
Tool

Voice Lab

saharmor

Framework for testing and evaluating voice agents across models, prompts, and personas.

D
Tool

Whisper

openai

General-purpose speech recognition trained on a large dataset of diverse audio.

D