I replicated Ng's RYS method and found that duplicating 3 specific layers in Qwen2.5-32B boosts reasoning by 17% and duplicating layers 12-14 in Devstral-24B improves logical deduction from 0.22→0.76 on BBH — no training, no weight changes, just routing hidden states through the same circuit twice. Tools included. Two AMD GPUs, one evening.
☆242Mar 20, 2026Updated 6 months ago
Alternatives and similar repositories for llm-circuit-finder
Users that are interested in llm-circuit-finder are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Agent learns to become the worlds top expert on SAT☆182Jun 16, 2026Updated 4 months ago
- Context Gateway is an agentic proxy that enhances any AI agent workflow with instant history compaction and context optimization tools☆645Aug 2, 2026Updated 2 months ago
- MCP server for Open and Async: AI tools to draft decision docs, run async standups, and triage sync vs. async work☆49Updated this week
- Turn any computer into a cloud server in 5 minutes.☆47Sep 1, 2026Updated last month
- A Python library that solves context window degradation in long-running LLM agents by moving memory management out of the model layer and…☆20Updated this week
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Turn a Big Mouth Billy Bass into a real-time voice assistant powered by Strands BidiAgent + Amazon Nova 2 Sonic on a Raspberry Pi 5☆90Oct 6, 2026Updated last week
- On-device models that know when they're wrong: every answer carries a confidence score for cloud handoff.☆270Jul 23, 2026Updated 2 months ago
- Ollama for classical ML models. AOT compiler that turns XGBoost, LightGBM, scikit-learn, CatBoost & ONNX models into native C99 inference…☆689Apr 16, 2026Updated 6 months ago
- Speedrunning LoRA fine-tuning: frozen task, frozen hardware, public wall-clock leaderboard. modded-nanogpt for fine-tuning.☆149Sep 12, 2026Updated last month
- A sourced model and short report: can Europe train a sovereign frontier AI model on the public compute it already owns, while gigawatt da…☆46Jun 15, 2026Updated 4 months ago
- Bayesian CausalImpact for Python — R-compatible Gibbs sampler in Rust (PyO3), 30x faster, no TensorFlow☆20Mar 26, 2026Updated 6 months ago
- ☆470Updated this week
- CDAF (Cached Descriptive Asset Files) - open sidecar format for video so AI agents stop re-analyzing the same footage. Spec, CLI, agent s…☆221Aug 28, 2026Updated last month
- The official code repo of Alignment Whack-a-Mole: Finetuning Activates Verbatim Recall of Copyrighted Books in Large Language Models☆101Mar 31, 2026Updated 6 months ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- SSH auth via browser passkeys (Touch ID / Face ID). No passwords, no SSH keys — just biometrics.☆28Mar 22, 2026Updated 6 months ago
- Full-screen text for any screen. The message lives in the URL, so there's no backend, accounts or storage.☆179Updated this week
- Your car as a chat-room agent: Raspberry Pi 5 + dashcam + local AI. CodeWatch's sibling for the garage.☆298Oct 9, 2026Updated last week
- ☆183Sep 22, 2026Updated 3 weeks ago
- Sub-millisecond VM sandboxes for AI agents via copy-on-write forking☆2,464Mar 21, 2026Updated 6 months ago
- Types generator for your Bun.sql queries☆112Updated this week
- Continual learning model trained from scratch on 8GB VRAM laptop with batch-1 stream of data.☆1,248Updated this week
- TurboQuant WASM SIMD vector compression — 3 bits/dim with fast dot product. Requires relaxed SIMD (Chrome 114+, Firefox 128+, Safari 18+,…☆323Apr 19, 2026Updated 5 months ago
- Markdown, mapped - the MD2HD CLI. Pull the repo, tell your agent to create an MD2HD map, visually comprehend complex topics and relations…☆136Aug 26, 2026Updated last month
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- Interactive HTML knowledge map from a folder of Markdown notes (Obsidian/gbrain) — themed force graph + growth timeline. Ships a prebuilt…☆73Jun 13, 2026Updated 4 months ago
- Self-hosted technical news inbox for curated feeds, article triage, source health, search, briefings, and saved/read history.☆36Updated this week
- Meta-harness optimization loop wired onto Islo sandboxes. POC: 0/5→5/5 in four proposer steps. Built on islo.dev.☆28May 5, 2026Updated 5 months ago
- Local-first multi-runtime AI cockpit (CLI + desktop + MCP). War-rooms, review receipts, open multi-model coding benchmarks. MIT.☆34Sep 7, 2026Updated last month
- ☆197Jul 21, 2026Updated 2 months ago
- make your framework hinge rusty (wow it's also written in rust too)☆57Jul 30, 2026Updated 2 months ago
- Open-source security gateway & static scanner for AI agents. Enforce role-based access control (RBAC), human-in-the-loop approvals, seg…☆54Oct 5, 2026Updated last week
- Unified Liminal World Editor, Procedural Engine & Game Creation Toolkit inspired by Radiant and Hammer. Optimised for low-power CPUs.☆149Updated this week
- Yet another minimal and lightweight terminal multiplexer built for the agent era.☆49Oct 1, 2026Updated 2 weeks ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Cursor for Data — a local-first AI workspace that understands your datasets: discovers relationships, builds semantic models, and answers…☆27Jul 25, 2026Updated 2 months ago
- Framework-agnostic Canvas loading animations as a lightweight Web Component.☆163Sep 12, 2026Updated last month
- CPU-first LLM inference server on llama.cpp. Runs useful models on free-tier ARM boxes; rewriting the input made it ~6x faster and more a…☆114Updated this week
- ☆196May 5, 2025Updated last year
- Rust crate for Forward Error Correction☆51Aug 8, 2026Updated 2 months ago
- A lightweight cli for running single-purpose AI agents. Define focused agents in TOML, trigger them from anywhere; pipes, git hooks, cron…☆897Oct 5, 2026Updated last week
- State machine guardrails for AI agents☆506Updated this week