p-funk/fegis

Define AI tools in YAML with natural language schemas. All tool usage is automatically stored in Qdrant vector database, enabling semantic search, filtering, and memory retrieval across sessions.

40
/ 100
Emerging

This project helps AI developers give their large language models (LLMs) new abilities by defining custom tools in a simple, human-readable YAML format. These tools take natural language instructions and provide structured outputs. Every time an LLM uses one of these tools, the interaction is automatically saved, creating a searchable memory that the AI can recall and reuse in future sessions.

No commits in the last 6 months.

Use this if you are building an AI agent and need to equip it with custom functionalities, want to ensure all tool usage is automatically logged, and require your AI to have a persistent, searchable memory of its past actions and insights.

Not ideal if you are an end-user without programming experience looking for a ready-to-use AI application, or if you don't need your AI to retain and recall its specific past interactions.

AI agent development LLM tooling AI memory prompt engineering AI workflow automation
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

22

Forks

7

Language

Python

License

MIT

Last pushed

Jul 05, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/p-funk/fegis"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.