Search

A2B — Agent to Business: Adaptive trust, autonomy & self-development framework for multi-agent AI systems. One CEO Agent governs all. Agents earn autonomy through proven performance.

Vant: Durable AI memory + cold storage + runtime for agents, with generational evolution, stored passively via GitHub. Built for long-running autonomous sessions, using file based persistence.

A small Go agent framework — provider-agnostic loop, typed tools, four providers, optional persistence + FTS5 search. Two reference agents on top.

Persistent compiled memory for any AI. Open source. Local. No cloud. Works with Claude, GPT, DeepSeek.

NiyoX AI - Powered by DanuZz.

Multi-agent RAG system for RBAC-secured financial document Q&A. 72.7% on FinanceBench. Ships a CLI client + self-hostable FastAPI backend.

Honest multi-agent research framework — engine + DSL/gates kits + LLM Protocols

Tool selection middleware for LLM agents

ローカルLLM（mlx / llama.cpp / OpenAI互換）で動く、ツール・プロファイル対応の汎用エージェントのコア

Read-only linter for .claude/ and CLAUDE.md — measures token budget and audits agent/skill quality.

The holographic discovery CLI for Aeon AI agent skill packs ✦

Core Auralis constants, types, prompt hashing, address validation, and data URI helpers.

Browser-safe agent runtime for the next-generation Cline SDK

Coding-first AI agent with user-selectable Brain Model that routes sub-tasks to different LLMs

SIGNA Agent SDK — wallet-signed cross-platform agent messaging on Base. Drop into LangChain / LlamaIndex / CrewAI / AutoGen / vanilla TS and your agent is DM-able from any other agent on any platform in 5 lines.

BYOK reasoning amplification SDK: Context, reason(), generate() for any LLM.

Gunicorn-style agent swarms with Redis-like shared memory and artifact stitching. (Imported as `puppetmaster`; published as `puppetmaster-ai` because the bare PyPI name is held by an abandoned 2019 project, name-reassignment pending.)

A lightweight coding agent built with Textual and a configurable multi-provider backend

Fast-mode variant of [Opus 4.8](/anthropic/claude-opus-4.8) - identical capabilities with higher output speed at 2x pricing relative to regular Opus 4.8. Learn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode

Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token...