llm-kb
← Back to products
Productbuilding

Looped Agent Framework: single-file config agent framework

A framework for building and deploying single-purpose AI agents using a single YAML config file. It uses LLMs as the agent's reasoning core, with all permissions defined at config time for security, and runs natively in Docker for easy deployment. Aimed at developers who want to quickly create secure, portable agents.

3 engagement·1 source·Mon, Jul 13, 2026, 10:12 AM
The Looped Agent Framework lets you define an agent entirely in an `agent.yaml` file. Built with Deno for sandboxed execution, it enforces security by requiring all permissions (filesystem, network, etc.) to be declared in the config, preventing runtime permission prompts. Agents are Docker-native, meaning they can be deployed anywhere Docker runs. The framework is designed for single-purpose agents, similar to OpenClaw or Hermes. No traction signals provided.

Entities

OpenClaw(concept)Docker(tool)Deno(tool)Hermes(concept)

Related

Product

Agent framework where the agent is a single file

A lightweight agent framework that defines the entire agent logic in one file. It uses LLMs to power autonomous decision-making and tool use, simplifying development for builders who want minimal boilerplate.

2 engagement·1 source·hackernews
Mon, Jul 13, 2026, 10:14 AM
Tool Release

AgentMaker: a new Python framework for building LLM agents and multi-agent systems

AgentMaker is a general-purpose Python framework for building LLM agents and multi-agent systems, featuring tools, memory, RAG, context engineering, guardrails, human-in-the-loop, and observability. It is released under MIT license on GitHub and PyPI.

32 engagement·1 source·github
Wed, Jul 8, 2026, 07:28 PM
Product

Governed multi-agent execution platform with trading engine

Melaya is a platform for designing and executing governed multi-agent workflows, paired with a trading engine. It uses LLMs to orchestrate agents while ensuring security and compliance, targeting operators who need controlled agent execution.

0 engagement·1 source·rss
Wed, Jul 8, 2026, 04:40 AM
RSS
Product

Declarative, sandboxed language for tool orchestration with LLMs

Skillscript is a small, declarative language for defining fixed procedures that local agents execute consistently, avoiding LLM drift and token waste. It lets users write and version agent behaviors instead of relying on model guesses each time. Solves the problem of unreliable, costly agent task execution for developers building local AI agents.

13 engagement·1 source·hackernews
Sun, Jul 12, 2026, 01:34 PM
Product

Attestor: open-source zero-trust boundary for autonomous AI agents

Attestor is an open-source execution boundary that enforces zero-trust security for autonomous AI agents. It uses LLMs to define and enforce policies that restrict agent actions, preventing unauthorized access or data leaks. This solves the problem of safely deploying autonomous agents in production environments.

3 engagement·1 source·hackernews
Sun, Jul 12, 2026, 07:54 AM