llm

Lowfat is a lightweight CLI tool that filters noisy command output before it reaches an AI agent, with plugins, shell integration, and usage stats for token savings.

Google’s Gemini 3.5 Flash announcement describes a frontier model aimed at agents and coding, with notes on speed, multimodal generation, and availability through the Gemini app, Google Antigravity, Gemini API, AI Studio, Android Studio, and Gemini Enterprise.

LLMCap is a proxy for LLM API calls that hard-stops requests when a dollar cap is reached, with support for major providers and companion tools for VS Code, CLI, and Windows.

An open-source CLI for testing LLM prompts across consistency, latency, cost, and behavior, with HTML reports and support for OpenAI and Anthropic.

oruk is a live broadcast intelligence API for real-time news. It offers REST endpoints, SSE streaming, webhooks, and an MCP server for use in AI apps and developer workflows.

A browser extension that lets users move AI chat threads between ChatGPT, Claude, and Gemini without retyping. It supports exporting/importing local .chatbridge files and emphasizes browser-only, local-first handling.

A two-part self-study course for building a tiny LLM stack from scalar autograd to a working chat assistant, with modules covering transformers, pretraining, instruction tuning, retrieval, tool use, and agent loops.

A Python framework for building AI agents as Python objects, with typed methods, stateful fields, and LLM-driven agentic methods. The repo includes installation steps, a quick start, examples, and notes on supported models and safety boundaries.

TokenPath is an API for token-level citations and attribution for LLM outputs. It resolves claims in generated answers back to source spans, uses attention-based tracing, and includes an endpoint for raw heatmaps.

VS Code extension that helps review large AI-generated diffs with local call graphs, file dependency graphs, and review cards that show blast radius and context before changes are pushed.

fenic is an open-source Python framework for semantic DataFrames, letting you use LLM-powered operators like extract, classify, summarize, and embed inside query pipelines.

Open-source terminal coding agent in Rust with LLM-native code understanding, shell safety, multi-provider support, and automatic failover.

Python package for recording real LLM API responses and replaying them in tests so LLM-driven code can run deterministically without live API calls.

Rust library for building modular, scalable LLM applications and agentic workflows. It supports multi-turn streaming, multiple model providers, vector store integrations, and agent runtime abstractions.

A native macOS Postgres GUI that can draft SQL from natural-language questions, using either a configured cloud model or Apple’s on-device Foundation Model on supported Macs.

An open-source, local-first canvas for editing LLM context as a graph. It lets users branch, prune, merge, and inspect the exact context sent to a model, with a desktop app, web demo, and support for Ollama and OpenAI-compatible endpoints.

An open-source reinforcement learning training loop for LLMs, spanning small CPU-friendly experiments like CartPole to async RLVR runs on GPU clusters. The repo highlights a compact codebase, quickstart commands, task customization, and support for algorithms like REINFORCE, PPO, GRPO, and RLOO.

An infinite canvas that turns LLM conversations, readings, and notes into an editable thought graph. It supports human-in-the-loop workflows, cited passages, replayable dependencies, and local-first backups.

Jargo is a Go framework for building realtime voice agents over WebRTC, with streaming STT→LLM→TTS pipelines, turn-taking, barge-in, and pluggable model providers.

Turo is a CLI proxy that reduces prompt text to content words to save tokens for coding agents. The repo shows install options, command examples, and support for multiple agents and modes.

A Python package and CLI for checking how closely an AI-generated answer reuses its source text, with support for verbatim matching, subsequence matching, quotation verification, and pipeline gating.

An open-source project that runs full games of Diplomacy between 7 LLM-controlled powers, with negotiation rounds, validated orders, and saved transcripts for replay and analysis.

An autonomous research system that runs on a single workstation and aggressively checks its own claims with adversarial self-verification, replication, and calibration audits.

A desktop browser that hallucinates web pages on the fly with an LLM, including interactive apps and customizable “lenses” for different styles of generated sites.