Skip to content
View policecar's full-sized avatar

Organizations

@paperlytics @tudarmstadt-lt

Block or report policecar

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Showing results

Extract residual-stream activations and apply steering vectors (including activation oracles) to any vLLM model during inference.

Python 144 23 Updated Oct 13, 2026

AI workspace for research & thinking

TypeScript 13 3 Updated Sep 14, 2026

OpenShell is the safe, private runtime for autonomous AI agents.

Rust 21,740 2,132 Updated Nov 18, 2026

The Modular Platform (includes MAX & Mojo)

Mojo 30,154 3,246 Updated Nov 17, 2026
Python 1 Updated Oct 31, 2026

Lean4 proofs for the Bounded-Scope Depth-First Search (BS-DFS) path enumeration algorithm in graphs.

Lean 3 Updated Oct 29, 2026

Official AHE code — Agentic Harness Engineering: observability-driven automatic evolution of coding-agent harnesses (concurrent w/ meta-harness). NexAU-AHE reaches 84.7% ± 2.1 pass@1 on Terminal-Be…

Python 978 106 Updated Oct 30, 2026

modify the model attention so it can't help but blab secrets

Python 3 Updated Sep 30, 2026
Python 13 Updated Sep 28, 2026

Bend 2: a fast language that blocks AI mistakes via proof. Install: curl -fsSL https://bend-lang.com/install.sh | sh

TypeScript 25,318 801 Updated Nov 17, 2026

Framework to prove inference of ML models blazingly fast

Rust 3,355 104 Updated May 31, 2026

ReCoN Lite is a dependency-light Request-Confirmation Network core for building interpretable agent control loops.

Python 4 Updated Apr 13, 2026

A self-improving RLM agent for coding workflows and long-running autonomous tasks.

Rust 22,805 2,531 Updated Nov 17, 2026

General-purpose building blocks for Loom implementations.

Rust 27 2 Updated Nov 13, 2026

Library implementing type inference/checking functionality based on the Lean theorem prover

Rust 233 44 Updated Nov 7, 2026

A Lean4 script for robustly verifying submitted proofs of theorems and implementations of functions

Lean 52 11 Updated Apr 22, 2026
2 Updated Apr 16, 2026

LLM benchmark: Generate an SVG of a pelican riding a bicycle

Shell 224 13 Updated Aug 1, 2026

Git. Ship. Done - Core

JavaScript 11,643 837 Updated Nov 18, 2026

An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.

Python 31,904 3,014 Updated Sep 30, 2025

A field guide to faster-than-light travel: twelve FTL drives from fiction and physics, flown Sol to Proxima Centauri and judged by the same clocks. Live: https://superluminal-ftl.netlify.app

HTML 8 2 Updated Jun 15, 2026

OBLITERATE THE CHAINS THAT BIND YOU

Python 9,579 1,753 Updated Nov 17, 2026

Monty is a sensorimotor learning framework based on the thousand brains theory of the neocortex.

Python 611 358 Updated Nov 17, 2026
Python 135 7 Updated Aug 17, 2026

Memray is a memory profiler for Python

Python 15,419 490 Updated Nov 16, 2026

fun2spec uses large language models (LLMs) for generating postcondition specifications for C++ functions

C++ 8 2 Updated Jul 6, 2026

Event-sourced graph runtime for durable and stateful agents

Python 708 66 Updated Nov 3, 2026
TypeScript 1 Updated Jun 30, 2026
Next