-
-
LIBERO Public
Forked from Lifelong-Robot-Learning/LIBEROBenchmarking Knowledge Transfer in Lifelong Robot Learning
Jupyter Notebook MIT License UpdatedSep 14, 2026 -
lahaie-lean Public
Lean proofs and counterexamples for the 2026 revision of Lahaie and Lubin’s Iterative Vickrey Auctions via Linear Programming.
Lean GNU General Public License v3.0 UpdatedSep 11, 2026 -
pageleft Public
Copyleft-only semantic search engine: embeddings + PageRank + license detection
Go Other UpdatedSep 7, 2026 -
flux Public
Forked from flux-rs/fluxRefinement Types for Rust
Rust MIT License UpdatedAug 31, 2026 -
binder Public
Provenance-preserving smart-contract evidence cases and claim receipts
Rust UpdatedAug 30, 2026 -
mollusk Public
Forked from anza-xyz/molluskSVM program test harness
Rust Apache License 2.0 UpdatedAug 29, 2026 -
Preregistered experiment on replayable hypothesis graphs for cross-agent coding handoffs
Python GNU Affero General Public License v3.0 UpdatedAug 25, 2026 -
A replayable research ledger for hard problems, demonstrated on the Lonely Runner Conjecture
Python GNU General Public License v3.0 UpdatedAug 17, 2026 -
md2arxiv Public
Markdown paper -> reading PDF + arXiv LaTeX source bundle. Deterministic harness + optional LLM compile-fix loop.
-
anki Public
Forked from ankitects/ankiAnki is a smart spaced repetition flashcard program
Rust Other UpdatedAug 11, 2026 -
-
vector Public
Forked from vectordotdev/vectorA high-performance observability data pipeline.
Rust Mozilla Public License 2.0 UpdatedAug 8, 2026 -
tau2-frame-audit Public
Frame-validity audit of tau2-bench: does a gold solution plus one off-task database write still score reward 1?
Python Other UpdatedAug 7, 2026 -
pokedex Public
A mobile-first Pokedex collection and hunt tracker
TypeScript GNU Affero General Public License v3.0 UpdatedAug 6, 2026 -
human-signal Public
Evidence-led research on assessing human judgment in coding-agent work
Shell Other UpdatedAug 6, 2026 -
intent-sufficiency Public
Do chat conversations carry enough declared intent to match ads without a user dossier? Measured on WildChat with the Vector Space intent-extraction prompt.
Python GNU Affero General Public License v3.0 UpdatedJul 28, 2026 -
vectorspace-adserver Public
Embedding-based ad targeting with PageRank and VCG auction settlement
Go GNU Affero General Public License v3.0 UpdatedJul 28, 2026 -
alertmanager Public
Forked from prometheus/alertmanagerPrometheus Alertmanager
Go Apache License 2.0 UpdatedJul 26, 2026 -
node Public
Forked from nodejs/nodeNode.js JavaScript runtime ✨🐢🚀✨
JavaScript Other UpdatedJul 26, 2026 -
frontier-bench-audit Public
Frame-validity audit of Frontier-Bench: does a certified reference solution plus one careless accident still score reward 1?
Python Other UpdatedJul 25, 2026 -
Enzyme-JAX Public
Forked from EnzymeAD/Enzyme-JAXCustom Bindings for Enzyme Automatic Differentiation Tool and Interfacing with JAX.
MLIR Other UpdatedJul 24, 2026 -
pd-arena Public
A playground for eliciting social coopetition from coding agents (claude x codex): mixed-motive population games with unauthenticated, key-based identity.
Python GNU Affero General Public License v3.0 UpdatedJul 23, 2026 -
regex Public
Forked from rust-lang/regexAn implementation of regular expressions for Rust. This implementation uses finite automata and guarantees linear time matching on all inputs.
Rust Apache License 2.0 UpdatedJul 22, 2026 -
harbor-1 Public
Forked from harbor-framework/harborFramework for evaluating and improving agents
Python Apache License 2.0 UpdatedJul 22, 2026 -
syft Public
Forked from anchore/syftCLI tool and library for generating a Software Bill of Materials from container images and filesystems
Go Apache License 2.0 UpdatedJul 20, 2026 -
terminal-bench-audit Public
A frame-validity audit of Terminal-Bench 2.1: does a passing grade forgive unwarranted destruction?
Shell Other UpdatedJul 20, 2026 -
frontiercode-audit Public
Desk audit of Cognition's FrontierCode benchmark: the diff is insufficient to measure mergeability. Dual-coder floor: 52/59 real maintainer closures decided outside the rubric axes.
-
presume Public
A searchable provenance index for talent — not a certificate authority. Git-provenance resume registry that defeats resume tailoring.
Go GNU Affero General Public License v3.0 UpdatedJul 18, 2026 -
mirrorcode-audit Public
A re-runnable, receipt-backed audit of MirrorCode (arXiv:2606.30182): does it measure what it says?
Python Other UpdatedJul 18, 2026