利用AI大模型，一键生成高清短视频 Generate short videos with one click using AI LLM.

See where your LLM tokens actually go — down to the individual tool call. A small, local, zero-config proxy + dashboard for token/cost tracking across Claude, OpenAI, Gemini.

The Rust SDK for building coding agents. Tool execution, LLM streaming, graph memory, sub-agent orchestration, MCP — as composable library functions.

The repo is finally unlocked. enjoy the party! The fastest repo in history to surpass 100K stars ⭐. Join Discord: https://discord.gg/5TUQKqFWd Built in Rust using oh-my-codex.

Extensions for the Zed editor

Swift Package for Headroom — context compression for LLM applications

Zed extension for Headroom — context compression for AI agents

Self-healing AI workbench with warm Droplet pools on DigitalOcean

Codebase vital signs for Claude Code — finds hotspots, diagnoses root causes, ranks fixes by ROI

nCPU: model-native and tensor-optimized CPU research runtimes with organized workloads, tools, and docs

AgentBudget is the ulimit for AI agents. Just like Unix systems have ulimit to prevent a single process from consuming all system resources, AgentBudget prevents a single agent session from consumi…

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server.

AI-powered PR reviewer with RAG over your codebase and Notion docs. Automatically analyzes PRs with cited evidence, enforces the Fact Gap philosophy (no claims without proof), and answers questions…

memcached implementation

DynamoDB Examples

DynamoDB Streams Kafka adapter

Archive Kafka topics to S3, with Zookeeper support

📟 Links to others' solutions to Projects (https://github.com/karan/Projects/)