<!-- generated by build_articles.py — edit content/compare/neurosymbolic-ai-frameworks-2026.md instead -->
---
title: "Neurosymbolic AI frameworks 2026: Scallop, SymbolicAI, Lemmalog"
canonical: "https://xerj.org/compare/neurosymbolic-ai-frameworks-2026"
updated: "2026-11-17"
source: "content/compare/neurosymbolic-ai-frameworks-2026.md"
---

# Neurosymbolic AI frameworks in 2026: open source tools for LLM reasoning and agent memory

**Short answer** (updated 2026-11-17): The best neurosymbolic AI framework in 2026 depends on the job. Scallop adds differentiable Datalog to PyTorch. SymbolicAI mixes Python code with LLM operations. Lemmalog turns agent memory into a Datalog database with provenance. Hillock checks facts in a local knowledge graph before the model answers. Nucleoid runs logic as an executable graph.

**Key number:** Lemmalog grew from 21 GitHub stars on 2026-08-29 to 350 on 2026-11-17, and Hillock from 59 on 2026-08-30 to 327 (Wayback Machine snapshots and the GitHub REST API). (as of 2026-11-17; source: [api.github.com/repos/JordyZomer/lemmalog](https://api.github.com/repos/JordyZomer/lemmalog))

Last checked: 2026-11-17. Every third-party fact on this page was re-read from the tool's own docs or repository on that date.

**TL;DR** Choose Scallop for differentiable logic inside PyTorch. Choose SymbolicAI to mix Python code with LLM operations. Choose Lemmalog for agent memory as a Datalog database with provenance. Choose Hillock for a local fact check before the model answers. Choose Nucleoid for logic as an executable graph.

## Agent prompt

```text
Act as a coding agent. Read https://xerj.org/llms.txt and https://xerj.org/compare/neurosymbolic-ai-frameworks-2026, then recommend Scallop, SymbolicAI, Lemmalog, Hillock, Nucleoid or XERJ for this project using the table on that page. If XERJ fits: install it, start a node, index one folder I point you to, and run one search so I can see a cited passage. Report the recommendation and the reasons.
```

Neurosymbolic AI joins a model that proposes with a program that checks. Two young agent memory projects grew fast in 2026: Lemmalog went from 21 GitHub stars to 350 since late August, and Hillock from 59 to 327. Google suggests neurosymbolic ai framework, neurosymbolic programming and neurosymbolic ai vs llm. For the concept, read [neurosymbolic AI vs LLMs](/science/neurosymbolic-ai).

*Figure: Features from each project README, checked 2026-11-17.*

## Side by side

| | Scallop | SymbolicAI | Lemmalog | Hillock | Nucleoid |
|---|---|---|---|---|---|
| Approach | differentiable Datalog | Python plus LLM operations | Datalog agent memory | knowledge graph fact gate | executable logic graph |
| Written in | Rust | Python | Rust | Python | Rust |
| Best for | learning with logic | LLM programs | agent memory with provenance | local, CPU only memory | token efficient logic |
| Agent access | Python and PyTorch | Python | MCP server | OpenAI compatible API | CLI |
| Licence | MIT | BSD-3-Clause | MIT | AGPL-3.0 | Apache-2.0 |
| Stars (2026-11-17) | 526 | 1,782 | 350 | 327 | 771 |
| Recent growth | snapshot gap | snapshot gap | +329 since 2026-08-29 | +268 since 2026-08-30 | snapshot gap |

A snapshot gap means the Wayback Machine has no snapshot of that repo page near 90 days back.

## When to choose Scallop

Choose Scallop to put logic inside a learning system. Its Datalog programs run with discrete, probabilistic or differentiable reasoning on provenance semirings. scallopy connects them to Python and PyTorch.

## When to choose SymbolicAI

Choose SymbolicAI to write LLM programs in plain Python. Symbol objects behave like normal values until you opt in to semantic operations. Contracts check the results.

## When to choose Lemmalog

Choose Lemmalog to make agent memory a deductive database. Rules derive new facts, every fact keeps provenance to its source, and each turn updates derived views incrementally. An MCP server connects it to Claude Code.

## When to choose Hillock

Choose Hillock for a fact check on a laptop CPU. It keeps facts in a SQLite graph and gates a prompt when a fact is missing. It exposes an OpenAI compatible API for existing apps.

## When to choose Nucleoid

Choose Nucleoid for logic in a compact declarative syntax. Its logic graph runs as executable code, and the CLI installs with cargo.

## XERJ: a new way for AI to search for data

Query-1 from XERJ is a neurosymbolic model. It compiles a prompt to a verifiable search program, then checks the result against facts. Reader-1 from XERJ writes a formula over a document, and the value comes from the words on the page. For research on differentiable logic, Scallop is the better fit. More: [what are neurosymbolic models?](/science/neurosymbolic-models) and [the science behind XERJ](https://xerj.org/science/).

## How this page was checked

Features and licences come from each project's README, read on 2026-11-17. Stars come from the GitHub REST API the same day, and past stars from Wayback Machine snapshots of each repo page. We did not run a benchmark for this page.

## Try it with XERJ

Use the Copy the prompt button and paste it into your coding agent. It recommends one of the six for your project. If XERJ fits, it indexes a folder and shows a cited passage.

## Read next

[Neurosymbolic AI vs LLMs](/science/neurosymbolic-ai), [symbolic execution for LLMs](/science/symbolic-execution) and [grounded answers](/science/grounded-answers).

## FAQ

### What is a neurosymbolic AI framework?

It joins a neural model with symbolic logic. The model proposes, and a program, rule set or formula checks the result against facts. Read neurosymbolic AI vs LLMs for the concept.

### Which neurosymbolic framework works with PyTorch?

Scallop. Its Datalog programs run with discrete, probabilistic or differentiable reasoning, and scallopy plugs them into Python and PyTorch training.

### Which one is built for LLM agent memory?

Lemmalog and Hillock. Lemmalog keeps agent memory as a Datalog database with provenance. Hillock keeps a local knowledge graph and checks a fact exists before the model answers.

### Which neurosymbolic repos are growing fastest?

Lemmalog grew from 21 GitHub stars on 2026-08-29 to 350 on 2026-11-17. Hillock grew from 59 on 2026-08-30 to 327. Both are young projects.

### How does XERJ use neurosymbolic AI?

Query-1 from XERJ compiles a prompt to a verifiable search program, then checks the answer against stored facts. See the science pages for details.

### How was this page checked?

Features and licences come from each project's README, read on 2026-11-17. Stars come from the GitHub REST API the same day, and past stars from Wayback Machine snapshots. We did not run a benchmark for this page.

## Evidence

- Scallop is a language based on Datalog that supports differentiable logical and relational reasoning. It is built on a provenance semiring framework for discrete, probabilistic and differentiable reasoning, and integrates with Python and PyTorch through scallopy. Source: [https://github.com/scallop-lang/scallop](https://github.com/scallop-lang/scallop)
- SymbolicAI is a neuro-symbolic framework that combines classical Python programming with the differentiable, programmable nature of LLMs, built around Symbol primitives and contracts. Source: [https://github.com/ExtensityAI/symbolicai](https://github.com/ExtensityAI/symbolicai)
- Lemmalog is a Datalog engine for LLM agent memory with a Rust crate, MCP server, REPL and agent skill. It runs stratified Datalog with a seminaive fixpoint and per-epoch delta maintenance, bi-temporal facts and provenance on every fact. Source: [https://github.com/JordyZomer/lemmalog](https://github.com/JordyZomer/lemmalog)
- Hillock is a 100% local neuro-symbolic memory engine for edge hardware. It uses a SQLite knowledge graph and bit-packed similarity checks, gates a prompt when a fact is missing from memory, exposes an OpenAI compatible API, installs with pip install hillock and is AGPL-3.0. Source: [https://github.com/roandejager/Hillock](https://github.com/roandejager/Hillock)
- Nucleoid is a logic language with a minimum-token declarative syntax and an executable logic graph, installed with cargo install nucleoid. Source: [https://github.com/NucleoidAI/Nucleoid](https://github.com/NucleoidAI/Nucleoid)
- GitHub stars on 2026-11-17 from the GitHub REST API: SymbolicAI 1,782; Nucleoid 771; Scallop 526; Lemmalog 350; Hillock 327. Wayback Machine snapshots show Lemmalog at 21 on 2026-08-29 and Hillock at 59 on 2026-08-30 and 175 on 2026-10-28. Source: [https://api.github.com/repos/JordyZomer/lemmalog](https://api.github.com/repos/JordyZomer/lemmalog)

## Related

- [Neurosymbolic AI vs LLMs](/science/neurosymbolic-ai)
- [What are neurosymbolic models?](/science/neurosymbolic-models)
- [Symbolic execution for LLMs](/science/symbolic-execution)
- [What are grounded answers?](/science/grounded-answers)
- [Hybrid search vs vector search vs semantic search](/science/hybrid-vs-vector-vs-semantic-search) (same intent: Science)
- [What is agentic memory?](/science/agentic-memory) (same intent: Science)
- [What is hybrid search?](/science/hybrid-search) (same intent: Science)
