#llm

该仓库未发布描述。

Millisecond microVM sandbox forking for AI agents on Kubernetes. Firecracker VMs that restore from memory snapshots in milliseconds, fork a running VM into N copies, and persist durable, versioned workspaces. Self-hostable, declarative CRDs.

Open-source AI model parameters database.

👩‍💻✍️ Prompt orchestration with Vue/React components. Compatible on any Node.js/browser runtime. No more context rendering and templating

An MCP server that acts as a bridge to query multiple OpenAI-compatible LLMs with MCP tool access. Just like rubber duck debugging, explain your problems to various AI "ducks" who can actually research and get different perspectives!

🔥 Java enterprise application development framework for full scenario: Restrained, Efficient, Open, Ecologicalll!!! 700% higher concurrency 50% memory savings Startup is 10 times faster. Packing 90% smaller; Compatible with java8 ~ java26; Supports LTS. (Replaceable spring)

Production-grade Kubernetes operator for nousresearch/hermes-agent: declarative spec, security defaults, S3 backups, OCI auto-update with rollback, SSA-based GitOps coexistence, OpenClaw migration.

Go SDK + CLI for building AI apps with a unified multi-provider LLM interface (OpenAI, Anthropic, Gemini, Ollama, HuggingFace, etc.), streaming, tool/function calling, secure key management, retries, and observability hooks.

The foundation layer for AI agents

Python framework for composable LLM workflows.

ContextGem: Effortless LLM extraction from documents

The website QA tool for your coding agent. 295+ audit rules across SEO, performance, security, accessibility and agent experience.

🦙🤖 Ollama for Hubot

AI governance infrastructure for agentic systems. Rust library behind systemprompt.io — MCP, A2A, OAuth2, audit trails, compile-time extensions. Evaluate with systemprompt-template.

Identity, memory, and soul for AI agents. Runs standalone or as part of a TPS office.

Turns the documentation you already write into tests that run. A failing test means your product and your docs disagree, and names the section.

C# implementation of LangChain. We try to be as close to the original as possible in terms of abstractions, but are open to new entities.

The transparent, composable harness for TypeScript agents. The same code runs the full agent loop on a local 4B model or a frontier API, with tool-call healing, verification, and a signed evidence receipt for every run.

🧃 Token weight loss. Lean output compaction for terminal-heavy agent workflows. Works as a native CLI tool or as an extension to popular coding and agent frameworks.

Local context engine for AI coding agents. Routes tasks to relevant files, tests, rules, and skills, supports prompt caching, and builds compact context packs for Claude Code, Codex, Cursor, MCP, and more.

Define AI agent roles in YAML and run them anywhere: CLI, API server, or autonomous daemon

Privacy-first LLM proxy and AI gateway - load balancing, multi-provider routing, API key management, usage tracking, rate limiting. Self-hosted. Zero knowledge of your prompts.

Universal LLM API client — 163 providers, 14 native language bindings, powered by a Rust core

Cognitive memory engine for AI agents — temporal decay, contradiction detection, autonomous consolidation, knowledge graph, ANN recall via HNSW. Embeddable Rust library with Python bindings; powers yantrikdb-server (HTTP gateway, MCP server, openraft cluster). Apache-2.0.

The agent loop for Rust — stream from 7 LLM protocols, run tools, loop until done. From a laptop to a Cloudflare Worker.

Multiplayer infrastructure for AI agents

Python SDK for AI agent monitoring, LLM cost tracking, benchmarking, and more. Integrates with most LLMs and agent frameworks including CrewAI, Agno, OpenAI Agents SDK, Langchain, Autogen, AG2, and CamelAI

Python video editing with JSON plans, local AI, and MCP tools.

AI partners for every person: multi-user, multi-agent memory, trusted tools, schedules, sandboxed workspaces, and chat.

Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.