#llm

Sandboxes for AI agents: TypeScript, Python, Go, Java and Ruby SDKs, the runtime CLI, an MCP server, and agent integrations. Firecracker microVMs.

Cortx — AI Agent runtime | Harness Agent + Agentic Loop | 43 tools | Python + TypeScript

coding agent built with golang

Enterprise MCP server for SQL Server with 20 tools for schema discovery, data operations, and administration.

Batteries-included helpers for building LLM-powered apps with the Vercel AI SDK and OpenRouter — automatic cost/usage tracking and pretty stream logging.

AI Agent framework on LangChain/LangGraph — multi-backend filesystem, sub-agents, summarization, security review, skills.

Production-grade observability and agentic AIOps for AI systems — OpenTelemetry-native across independent polyglot apps; GenAI semantic conventions with token/cost attribution; sub-2s detection on a hot path that skips the datastore; LLM agents that find root cause and notify. ClickHouse + Langfuse. 100% self-hosted — no vendor lock-in.

A layered proxy to ensure almost near full compatibility with OpenAI , worry native tooling mapped like search and sandboxes

Go port of pxpipe core - cut Claude Code token usage by rendering text context as images

Local MCP daemon that compresses your codebase before sending it to Claude 41-89% token reduction

A composable, substrate-independent agent in IPython.

A blazing-fast Markdown-to-ANSI CLI for terminal rendering, LLM streaming, and syntax highlighting. 📝

Deploy local LLMs behind your own managed API server - vLLM or llama.cpp in isolated environments, API keys, workspaces, usage tracking

Large-scale JSON/JSONL data analysis CLI using local LLMs

No repository description published.

OpenCode plugin provider for 9Router — FREE AI Router & Token Saver. 40+ providers, 100+ models.

Offline CLI for per-prompt coding-assistant token usage

No repository description published.

OpenAPI → Agent tools with risk, confirmation, and lint. Offline CLI. Export OpenAI / LangChain / MCP. Apache-2.0.

A tiny, dependency-free taxonomy for AI agent tool-call failures: retry, re-prompt, or escalate — with model-ready hints.

Beautiful CLI for benchmarking Ollama & LM Studio LLM inference speed

No repository description published.

LYT™ — Link Your Think: federated markdown vaults — the storage architecture for AI-native knowledge work, AI-first by design. Mint vaults you own, weave meshes you share, forge Your Pod. Markdown-in-Git, YON-structured, never phones home. 7 npm packages under @younndai. Apache-2.0 · free forever · alpha. By YounndAI — younndai.com.

A CLI tool that extracts structured knowledge notes from source files using a local LLM, generates embeddings, and stores them as a searchable knowledge base.

Hindsight memory plugin for OpenCode with Claude Code-aligned per-turn auto-recall

No repository description published.

The agent harness you can read, replay, and rewind. One Effect boundary, five superpowers: deterministic replay, fork-at-any-turn, bisect, free CI tests, cost accounting.

No repository description published.

DockCode transforms the way you interact with Docker. Stop memorizing complex CLI flags and documentation—simply tell DockCode what you want to achieve in plain English, and watch it orchestrate your containers, images, networks, and volumes in real-time.

AgentBus Python Client