Traction scoreGitHub stars can be faked, so popularity alone can be misleading. Traction Score looks for broader signs of recent attention, adoption, and active maintenance.
The Synalinks framework provides a Keras-inspired API for developing neuro-symbolic LM applications, integrating data models with decision logic and agentic workflows.
WHO IT'S FOR
AI agent / automation builders
building neuro-symbolic LM applications and agents
ML engineers
training LMs with in-context reinforcement learning
AI research engineers
implementing neuro-symbolic reasoning and self-critique
Compatible AgentsThe repository documents support for these agents. The skills may also work with other agents that can load SKILL.md files, but they may need some setup or small changes.
Installs: The complete synalinks skill, installed in the detected agent's user-level skills directory for use across projects. · Claude Code, Codex, OpenCode, pi
Before you start
Node.js with its bundled npx command must already be installed.
Run this terminal command to install the synalinks skill globally for the detected supported agent.
[target Python file]: destination path for the example code
[language-model identifier]: a configured model identifier; the documented example uses ollama/mistral
[question]: the question the program should answer
Use the synalinks skill to create a minimal asynchronous structured Q&A program in [target Python file]. Define Query and Answer DataModels, build a Generator and Program using [language-model identifier], invoke it with [question], check for a None result, and print the resulting prettified JSON. Keep module constructors keyword-only and await asynchronous calls. Do not modify other files.
Claude
Codex
Cursor
Gemini CLI
Copilot
Windsurf
OpenCode
Goose
DeepSeek