Developer Tools●●Solid
Bonsai - A TypeScript-first sandboxed expression evaluator
Replaces eval() with typed sandboxing while JEXL and jsonata already exist.
SlickSolve My Problem
danfry
104mo ago
Back to browse
GitHub Repository
Deterministic boolean algebra engine — evaluates expressions, detects contradictions, audits logic rules. MCP server, NL layer, REST API, CLI, Streamlit UI.
6 starsPython
I Built an LLM Engine, That Test LLM on Boolean Logic
by shrvx·Jun 8, 2026·2 points·0 comments
AI Analysis
●●SolidSolve My ProblemNiche Gem
Catches contradictions in AI decision rules that LLMs miss, in under 10ms.
Strengths
- •Zero dependencies with 90 passing tests and sub-10ms evaluation time.
- •MCP server integration lets Claude Desktop audit agent logic directly.
- •Multiple interfaces (CLI, REST API, Streamlit UI) for different workflows.
Weaknesses
- •Boolean algebra solving is well-solved territory with SymPy and PyEDA existing.
- •Only 3 GitHub stars suggests limited real-world adoption so far.
Category
Target Audience
AI agent developers, teams building rule-based decision systems
Similar To
SymPy · PyEDA
Post Description
I have built an LLM Engine, That tracks SOTA Models hallucinating over basic Logical Reasoning that can be solved through Quine-McClusky method mathematically. I am using it to build diverse use cases.
Let me know if you want me to try it out on something.
Similar Projects
AI/ML●●●Banger
A new benchmark for testing LLMs for deterministic outputs
Finally separates JSON validity from actual value hallucination in LLM outputs.
Big BrainSolve My Problem
khurdula
60302mo ago
AI/ML●●Solid
AptSelect – A local LLM client for parallel testing and evaluation
Parallel LLM testing across providers when LangSmith costs way more.
Solve My ProblemNiche Gem
dhavalt
301mo ago
AI/ML●●●Banger
LogicPearl – Synthesizing deterministic executable logic from traces
Deterministic rule extraction from traces — same input always produces same output, no tokens.
Big BrainZero to One
kenerwin88
443mo ago
AI/ML●●Solid
Rubric – test what your LLM agent did, not just what it said
Tests tool calls and trace quality when LangSmith only checks output strings.
Solve My Problem
kareemrashed
101mo ago
Developer Tools●●Solid
Boolean-query-parser – From a 4-hour hack to 3k downloads
Zero-dependency parsing plus regex support and implicit-AND is a practical combo — you can run the same parser in the browser via WebAssembly for quick demos. It’s a tidy, usable tool for projects that need boolean filtering without a Lucene stack, but it doesn’t attempt anything novel (no ranking, tokenization pipelines, or scaling benchmarks), so it’s best as a lightweight building block rather than a drop-in search engine.
Niche GemShip It
TheBuc
115mo ago