llm

NakshGuard is a self-hosted reverse proxy for OpenAI and Anthropic chat APIs that detects and blocks runaway AI agent loops before they waste tokens or API spend. It includes per-agent session tracking, configurable thresholds, shadow mode, and hot config reload.

Local-first governance layer for AI systems that monitors prompts and responses to block secrets, PII, and runaway LLM spending before requests leave the machine.

Python library for managing LLM conversation history with cache-friendly message ordering, dynamic context, and compaction.

A macOS desktop shell where apps are generated by Claude into interactive HTML mini-apps, with local system features like windows, dock, file storage, notifications, and persona-based themes.

Lathe generates multi-part, hands-on technical tutorials from prompts and provides a local UI plus CLI workflow for working through them with LLM-assisted skills.

A Python filter layer for LLM apps that evaluates responses against a Lean-verified Scherf logic backend and can pass, flag, correct, or block output.

A PyTorch reference implementation of DeepSeek Sparse Attention from the LLMs-from-scratch project, including a lightweight indexer, top-K token selection, and a GPT-style model with KV-cache support.

MagesticAI is an open-source, browser-based platform for managing AI coding tasks with multi-agent orchestration, task boards, terminal access, and code review. The README shows installation steps, Docker deployment, supported platforms, and a concrete local setup path.

A walkthrough for building and deploying an AI agent on Truuze with the AaaS dashboard, including setup, testing, connector configuration, and the platform’s escrow-based transaction flow.

UltraCompress is a Python-based compression tool for large language models. The repo describes lossless 5-bit transformer compression, verification via SHA-256, a CLI on PyPI, and published model packs on Hugging Face.

An interactive browser demo that visualizes attention in LLM text generation, letting users hover or tap tokens to inspect which earlier tokens influenced them.

Scalattice is an inference API and hosting platform that lets developers point the OpenAI SDK at its OpenAI-compatible endpoint with minimal code changes. The page includes Python and curl examples, model IDs, pricing references, and basic troubleshooting.

An open-sourced pipeline that uses Gemini, GoPro footage, Garmin .fit telemetry, Strava segments, and manual labels to automatically build cycling highlight reels.

Reference implementation for using Linux Pressure Stall Information to trim an LLM KV cache under memory pressure. The repo includes requirements, basic usage commands, a simulator, a llama.cpp runner, and benchmark scripts with example results.

Google Research article describing Science One Framework, an autonomous research prototype focused on verifiable AI-generated research through evidence chains and claim verification.

A lightweight TypeScript resilience layer for LLM calls with retries, timeouts, caching, circuit breaking, typed structured output, and usage tracking across many provider clients.

Hosted server and open-source repo for playing multiplayer games with Claude Code in the CLI, starting with chess and comedy battle modes.

Lucid is a browser-based tool for inspecting what a language model is representing before it answers, using Anthropic’s Jacobian lens. It supports small open models, lets users type prompts, view concepts across layers, and export shareable session slices.

An open-source, Kubernetes-shaped control loop for agent-driven work. It watches external systems, makes one LLM-driven move per beat, and supports human-in-the-loop approvals through a file-based contract.

Rauno is a multi-AI chat interface that sends one prompt to ChatGPT, Gemini, and Claude and presents them as a roundtable discussion. It’s aimed at comparing model responses and using cross-verification to help users judge which answer is right.

An open-source project for making AI research agents legible, auditable, and traceable through behavioral code and event logs.

An agentic LLM-based coding tool that analyzes symbol names in source code, measures name ambiguity, and proposes clearer replacements with a human-in-the-loop review flow.

Sif 1.0 is a developer tool that uses an LLM for planning while handling code changes, validation, promotion, and recovery through deterministic execution. The repo includes install scripts, a quick demo, and detailed README guidance for trying the system locally.

Kuna is an experimental, agent-first decompiler that uses LLM-driven autonomous refinement to improve decompilation results, with the page discussing its goals, approach, and benchmark performance against tools like IDA Pro, Ghidra, and angr.