Mastodon discussion Discussions Jun 14

I've been building a simple framework to run Ollama-based LLMs with full agentic tooling, entirely on your local machine...

by Anthropy

I've been building a simple framework to run Ollama-based LLMs with full agentic tooling, entirely on your local machine.I'm calling it #WyvernClaw 🐉It has:- subagents (can specify which LLM, defaults to preset)- configurable system prompts, selectable tools- websearch, http fetching (with beautifulsoup to make it more LLM-friendly)- sandboxing for file read/write tools and SSRF protection for http fetch- session persistence- basic auth#AI

Read Original

Agents

Metadata

Reblogs Count: 1
Replies Count: 1
Account: anthropy@mastodon.derg.nz

Mastodon discussion 22m ago

Re-watching Frieren, I just had an epiphany: demons evolved to use human language to fool humans, all the while not unde...

Re-watching Frieren, I just had an epiphany: demons evolved to use human language to fool humans, all the while not understanding any of the underlying actual meaning of the words....

Mastodon discussion 22m ago

👀 Ah, the age-old quest of "Who does #Anubis actually stop?" - a riveting tale of a tech-savvy #Sherlock attempting to o...

👀 Ah, the age-old quest of "Who does #Anubis actually stop?" - a riveting tale of a tech-savvy #Sherlock attempting to outsmart an #HTTP #proxy with a patch, a kernel, and a sprink...

Mastodon discussion 27m ago

I've been building a simple framework to run Ollama-based LLMs with full agentic tooling, entirely on your local machine...

Metadata

Related

Re-watching Frieren, I just had an epiphany: demons evolved to use human language to fool humans, all the while not unde...

👀 Ah, the age-old quest of "Who does #Anubis actually stop?" - a riveting tale of a tech-savvy #Sherlock attempting to o...

Running a 28.9M parameter LLM on an $8 microcontrollerhttps://github.com/slvDev/esp32-ai#ai #github #llm