A distributed filesystem backend for your AI agent in a single API, just like a database or storage system.
Pi coding-agent backend for skelm with full permission enforcement
A composable agent runtime — pair any frontend with any agent backend over one shared extension layer
First-party skelm agent backend with native permission enforcement
Setup helper for General Augment, the agent backend for your app.
PlayCraft monorepo 内部共享库，给 CLI Agent / Backend / Realtime / Messenger 提供可复用的通用能力。
TypeScript SDK for General Augment, the agent backend for your app.
WhatsApp-only agent backend built on Nexusbert architecture.
Agent-agnostic CLI for teammates. Routes tasks, manages handoffs, and plugs into any coding agent backend.
Local runner that serves Lexia built frontend with API/WS proxy to your agent backend
Raxode coding agent backend and legacy TUI built on Praxis.
Self-hosted AI agent backend powered by GitHub Copilot SDK
Follow these steps to run the LangGraph agent backend that powers the Agentic Chat example. Commands assume you are in the monorepo root unless noted.
Follow these steps to run the LangGraph agent backend that powers the Agentic Chat example. Commands assume you are in the monorepo root unless noted.
MCP server for Ridge portfolio metrics from the knowledge-base agent backend
Pi Agent backend for the Actant platform — built on pi-agent-core and pi-ai
LLM-powered agent backend using Vercel AI SDK
Abra Evolve CLI - Connect to your AI agent backend
Shared agent backend abstraction for CLI-based AI agent spawning. Used by conduit-vscode and aahp-runner.
Turn a function into an `http.Agent` instance
An HTTP(s) proxy `http.Agent` implementation for HTTPS
Maps proxy protocols to `http.Agent` implementations
[](https://www.npmjs.com/package/@aws-sdk/util-user-agent-node) [](https://www.npmjs.com/
HTML5 backend for React DnD
Faure orchestre un agent codeur et un agent git via GitLab CI/CD et un backend OpenAI-compatible (mlx_lm, Ollama, OpenAI...).
Enables AI agents in Collavre to use OpenClaw as their LLM backend
Yorishiro is a CLI-based LLM agent that supports multiple providers (Anthropic, OpenAI, Ollama), built-in tools for file operations and command execution, MCP server integration, and plan mode.
Claude Swarm enables you to run multiple Claude Code instances that communicate with each other via MCP (Model Context Protocol). Create AI development teams where each instance has specialized roles, tools, and directory contexts. Define your swarm topology in simple YAML and let Claude instances collaborate across codebases. Perfect for complex projects requiring specialized AI agents for frontend, backend, testing, DevOps, or research tasks.
EnhanceSwarm transforms Claude into a sophisticated development team with specialized agents for Backend, Frontend, QA, and Integration. Features detached orchestration, Bullet Train deep integration, automatic worktree merging, and comprehensive logging. Built for production Rails and Bullet Train applications.
Heap Periscope Agent offers deep insights into your Ruby application's memory behavior. It collects and reports real-time Garbage Collection (GC) statistics and object allocation patterns, empowering developers to identify memory leaks, optimize usage, and enhance performance. This gem is the backend agent for memory monitoring. To visualize the collected data, you must also install the companion gem, heap_periscope_ui The agent's visualizer is available here: - Gem: https://rubygems.org/gems/heap_periscope_ui - Repository: https://github.com/codepawpaw/heap_periscope_ui
Give an AI agent a disposable computer: run shell commands, read/write files, expose ports. Pluggable backends (Docker today, E2B/Cloudflare later).
pikuri-vectordb gives a pikuri-core agent a +vectordb_search+ tool over a local document corpus — agentic search, the agent decides when to retrieve. Ships a swappable backend (a pure-Ruby +Backend::InMemory+ for teaching, plus thin +Backend::Qdrant+ / +Backend::Chroma+ HTTP clients for persistence — Qdrant recommended), a chunker, an embedder wrapper over +RubyLLM.embed+, and an optional +Reranker::LlamaServer+ that speaks +/v1/rerank+ against a cross-encoder model. Text extraction goes through +Pikuri::FileType.read_as_text+ in pikuri-core, which handles plain text / Markdown / PDF; HTML extraction is a deferred follow-up. Hosts wire the feature via +c.add_extension Pikuri::VectorDb::Extension.new(...)+ inside the +Agent.new+ block — same opt-in shape as +pikuri-tasks+ / +pikuri-skills+. The bundled +Pikuri::VectorDb::LIBRARIAN+ persona is the privilege-separated sub-agent counterpart for hosts that want recall to flow through a child rather than the parent's context. Three model endpoints in the full setup — chat (via ruby_llm), an embedder (via +RubyLLM.embed+), and an optional reranker (HTTP +/v1/rerank+). A single +llama-server+ in router mode serves all three by default, loading each cached GGUF on demand; see the gem's README for details.
The Cloud Debugger API allows applications to interact with the Google Cloud Debugger backends. It provides two interfaces: the Debugger interface and the Controller interface. The Controller interface allows you to implement an agent that sends state data -- for example, the value of program variables and the call stack -- to Cloud Debugger when the application is running. The Debugger interface allows you to implement a Cloud Debugger client that allows users to set and delete the breakpoints at which the state data is collected, as well as read the data that is captured. Note that google-cloud-debugger-v2 is a version-specific client library. For most uses, we recommend installing the main client library google-cloud-debugger instead. See the readme for more details.
A comprehensive Ruby implementation of a Knowledge-Based System featuring: • RETE Algorithm: Optimized forward-chaining inference engine with unlinking optimization for high-performance pattern matching • Declarative DSL: Readable, expressive syntax for rule definition with built-in condition helpers • Blackboard Architecture: Multi-agent coordination with message passing and knowledge source registration • Flexible Persistence: SQLite (durable), Redis (fast), and hybrid storage backends with audit trails • Concurrent Execution: Thread-safe auto-inference mode for real-time processing • AI Integration: Native support for LLM integration (Ollama, OpenAI) for hybrid symbolic/neural reasoning • Production Features: Session management, fact history, query API, statistics tracking Perfect for expert systems, trading algorithms, IoT monitoring, portfolio management, and AI-enhanced decision systems.
No description provided.
No description provided.
No description provided.