ChampagneWiki.
AI

Build with AI

Agent frameworks, coding agents, MCP, IDEs, and AI app-building tools.

Agents, Pipelines & Tooling

Build with AI.

Agent frameworks, autonomous coding tools, AI-native IDEs, and the protocols and infrastructure that connect models to real software.

Agent safety:

Agents frequently run with elevated permissions and can execute shell commands or modify files without confirmation. Avoid granting full root or drive access — a container, VPS, or VM is strongly recommended for anything autonomous.

Pill key: Official / frontier Tool / app Open-source Community Discord Use with caution

Agent frameworks give a language model the ability to plan, call tools, and act autonomously instead of just answering a single prompt. The space splits into single-agent frameworks built for one autonomous actor, and multi-agent orchestration frameworks designed to coordinate several agents working together on the same task.

AutoGPT

183K Stars

The original autonomous agent framework that sparked the agent movement, with modular architecture and forge-based agent building.

LangChain / LangGraph

Foundational

The foundational library for agents, chains, and memory — LangGraph adds stateful, controllable agent orchestration on top.

Google ADK

Apache 2.0

Code-first Python toolkit for sophisticated multi-agent orchestration with built-in evaluation, model-agnostic but tightly integrated with Google's ecosystem.

Pydantic AI

MIT

Type-safe agent framework from the creators of Pydantic, with 20 model providers, built-in observability, and MCP/A2A protocol support.

Open-source agent orchestration
  • MetaGPT — multi-agent framework where agents collaborate as programmers, designers, and testers, Apache 2.0
  • AWS Labs Agent Squad — flexible multi-agent orchestration with intent classification, pre-built for Bedrock and Lex
  • A2A Protocol — Google's Agent2Agent open protocol for interoperability between agentic applications, donated to the Linux Foundation
  • Langflow — open-source visual canvas for building and deploying agents with 1000+ integrations across frameworks
  • PocketFlow — a 100-line minimalist LLM framework for lightweight agent workflows

As agent ecosystems mature, standardized protocols are emerging so agents built on different frameworks can still talk to each other, share memory, and expose tools safely.

Memory & context infrastructure

Long-running agents need persistent memory beyond a single context window. Tools like Letta, dedicated memory-engine APIs, and local-first memory lifecycles (e.g. Ring Memory) let agents store, retrieve, and reuse context across sessions without re-processing everything from scratch each run.


These agents operate directly inside your terminal or repository — reading code, writing patches, running tests, and iterating without constant hand-holding. Most fall into either an IDE-integrated assistant or a fully terminal-native harness that manages its own subagents and memory.

OpenHands

Full Agent

Full-featured open-source AI software engineer, formerly OpenDevin, built for end-to-end autonomous development tasks.

Gemini CLI

Apache 2.0

Open-source agent bringing Gemini's capabilities directly into your terminal, with code generation and shell execution.

Mini-SWE-agent

Lightweight

Lightweight coding agent purpose-built for repository and issue-fixing workflows and agentic SWE experiments.

Continue

IDE-Native

Open-source AI code assistant that connects any model into custom autocomplete and chat inside your IDE.

Coding agent skills & workflow frameworks

A newer layer of tooling packages entire development processes — planning, TDD, code review, spec refinement — as reusable "skills" agents can load. These sit on top of Claude Code, Codex, and other agents rather than replacing them, and are worth exploring once you've settled on a base agent.


Not every AI workflow needs custom code. Visual builders let you wire models, tools, and data sources together on a canvas, which is often the fastest path from idea to working prototype.

Langflow

Apache 2.0

Open-source AI workspace with a visual canvas, 1000+ integrations, and multi-framework support (Agno, LangChain, Google ADK).

Flowise

Drag & Drop

Drag-and-drop builder for LLM apps and RAG agents, popular for fast internal tool prototyping.


Beyond chat-based coding help, these are full environments and utilities built specifically around AI-assisted development — from complete IDE replacements to focused CLI utilities that plug into whichever agent you're already using.

Cursor

AI-Native IDE

A full IDE built around AI-assisted multi-file editing, one of the most widely adopted AI-first development environments.

Windsurf

Fluid Editor

AI-native IDE combining code editing with continuous AI assistance across the whole development flow.

Devcontainer/Sandbox Runtimes

Safety Layer

Portable sandbox execution environments that constrain filesystem and network access, reducing blast radius when running autonomous agents.

Guardrails, red-teaming & responsible AI dev
  • NeMo Guardrails (NVIDIA) — programmable safety rules and dialog flows for LLM apps, integrates with LangChain/LangGraph
  • Guardrails AI — input/output validation for PII, toxicity, and prompt injection with 50+ pre-built validators
  • Microsoft PyRIT — automated red-teaming framework for generative AI with multi-modal attack support
  • Presidio (Microsoft) — detect, redact, and anonymize PII across text and images

For teams or individuals who want a complete AI stack running on their own infrastructure — chat interface, model serving, and agent orchestration all self-hosted rather than stitched together from cloud APIs.

Open WebUI

Most Popular

The most widely used self-hosted ChatGPT-style interface, supporting local and remote model backends.

LocalAI

MIT

Self-hosted OpenAI-compatible API engine running LLMs, vision, voice, image, and video models on any hardware.

On-prem enterprise AI knowledge platforms

Several open-source projects now offer full "ChatGPT replacement" stacks with RAG, access controls, and audit logging built in — suited for teams that need an internal AI knowledge base without sending data to a third-party cloud. Worth cross-referencing with the Local AI page for model-serving setup.

Distinct from coding agents, this class of tool lives in your everyday messaging apps — Telegram, WhatsApp, Discord, Slack — and handles real-world tasks like email, scheduling, and browsing on your behalf rather than writing code.

OpenClaw

Viral / OSS

Open agent platform that runs on your machine and works from the chat apps you already use — WhatsApp, Telegram, Discord, Slack, Teams. Broad ecosystem with a large community skill marketplace (Clawhub), though cross-session memory needs manual setup.

Hermes Agent

Self-Improving

MIT-licensed agent from Nous Research with a built-in closed learning loop — it writes reusable skills from completed tasks and builds persistent memory automatically. Supports 200+ models and can migrate an existing OpenClaw setup directly.

OpenClaw vs. Hermes Agent

These two are often run together rather than as competitors: OpenClaw contributes ecosystem breadth and multi-channel orchestration, while Hermes Agent contributes the persistent memory and self-improving skill layer that OpenClaw lacks out of the box. A common setup runs Hermes as a high-level planner on top of OpenClaw's tools.

On this page