typedef-ai/fenic

Declarative context engineering for agents

45
/ 100
Emerging

Provides deterministic and semantic transforms (extract, chunk, embed, summarize) over Python and SQL to construct typed, bounded tool outputs while offloading inference outside the agent's context window. Integrates with any agent framework via MCP servers or direct Python functions, reducing context bloat so agents can focus on reasoning without framework lock-in.

444 stars.

No Package No Dependents
Maintenance 13 / 25
Adoption 10 / 25
Maturity 9 / 25
Community 13 / 25

How are scores calculated?

Stars

444

Forks

27

Language

Python

License

Apache-2.0

Last pushed

Mar 12, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/typedef-ai/fenic"

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