A plan-don't-react framework for LLM agents. The model emits a typed dataflow plan once; the runtime executes it; the model never reads state it shouldn't.
Cross-referenced across 55 tracked directories
#3018
Popularity Rank
1 / 55
Listed In
Emerging
Adoption Stage
7/13/2026
Created
10
GitHub Stars
2
Forks
1
Open Issues
7/14/2026
Last Commit
Recently added to the ecosystem
Score: 100/100
0 dependency vulnerabilities found
wolffiex
SDK for building AI agents with Claude Code's capabilities. Programmatically interact with Claude to build autonomous agents that can understand codebases, edit files, and execute workflows.
...morecan1357
Unified LLM API with automatic model discovery and provider configuration
zensation-ai
Neuroscience-inspired memory algorithms: FSRS spaced repetition, Hebbian learning, Ebbinghaus decay, emotional tagging, Bayesian confidence propagation. Zero dependencies.
...more