{"id":45872508,"url":"https://github.com/ryvos/ryvos","last_synced_at":"2026-04-02T19:51:28.109Z","repository":{"id":340702666,"uuid":"1163850643","full_name":"Ryvos/ryvos","owner":"Ryvos","description":"Open-source autonomous AI assistant with 5-tier security, 62 tools, 14 LLM providers. Written in Rust. Single binary.","archived":false,"fork":false,"pushed_at":"2026-03-14T09:37:15.000Z","size":2652,"stargazers_count":1,"open_issues_count":12,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-03-14T18:10:09.559Z","etag":null,"topics":["ai","ai-agent","ai-assistant","assistant","autonomous","autonomous-agent","chatbot","cli","discord-bot","docker","llm","mcp","ollama","open-source","rust","security","self-hosted","telegram-bot"],"latest_commit_sha":null,"homepage":"https://ryvos.dev","language":"Rust","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Ryvos.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":"CONTRIBUTING.md","funding":".github/FUNDING.yml","license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null},"funding":{"github":["aayushmishraaa"]}},"created_at":"2026-02-22T08:48:39.000Z","updated_at":"2026-03-14T09:37:19.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/Ryvos/ryvos","commit_stats":null,"previous_names":["ryvos/ryvos"],"tags_count":13,"template":false,"template_full_name":null,"purl":"pkg:github/Ryvos/ryvos","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Ryvos%2Fryvos","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Ryvos%2Fryvos/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Ryvos%2Fryvos/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Ryvos%2Fryvos/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Ryvos","download_url":"https://codeload.github.com/Ryvos/ryvos/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Ryvos%2Fryvos/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":30622095,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-17T08:10:05.930Z","status":"ssl_error","status_checked_at":"2026-03-17T08:10:04.972Z","response_time":56,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai","ai-agent","ai-assistant","assistant","autonomous","autonomous-agent","chatbot","cli","discord-bot","docker","llm","mcp","ollama","open-source","rust","security","self-hosted","telegram-bot"],"created_at":"2026-02-27T10:50:08.149Z","updated_at":"2026-04-02T19:51:28.099Z","avatar_url":"https://github.com/Ryvos.png","language":"Rust","funding_links":["https://github.com/sponsors/aayushmishraaa"],"categories":[],"sub_categories":[],"readme":"\u003cdiv align=\"center\"\u003e\n\n\u003cimg src=\"docs/logo.png\" alt=\"Ryvos — Open-Source AI Agent Runtime\" width=\"120\"\u003e\n\n# Ryvos\n\n### Open-source AI agent runtime built in Rust. Self-hosted. 15–30 MB RAM. 18+ LLM providers.\n\n[![GitHub Stars](https://img.shields.io/github/stars/Ryvos/ryvos?style=flat\u0026color=yellow)](https://github.com/Ryvos/ryvos/stargazers)\n[![MIT License](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)\n[![Rust 1.75+](https://img.shields.io/badge/rust-1.75%2B-orange.svg)](https://www.rust-lang.org)\n[![Release](https://img.shields.io/github/v/release/Ryvos/ryvos?color=F07030)](https://github.com/Ryvos/ryvos/releases)\n[![CI](https://img.shields.io/github/actions/workflow/status/Ryvos/ryvos/ci.yml?label=CI)](https://github.com/Ryvos/ryvos/actions)\n[![Platform: Linux macOS](https://img.shields.io/badge/platform-linux%20%7C%20macos-lightgrey.svg)](#quick-start)\n\n**Goal-Driven Agents · 18+ LLM Providers · 86+ Tools · DAG Workflows · MCP-Native · Constitutional AI Safety · Single Binary**\n\n[Quick Start](#quick-start) · [Why Ryvos](#why-ryvos) · [Features](#features) · [Architecture](#architecture) · [Security](#security) · [Roadmap](#roadmap)\n\n[Website](https://ryvos.dev) · [Cloud](https://cloud.ryvos.dev) · [Docs](https://ryvos.dev/docs)\n\n\u003c/div\u003e\n\n---\n\n```bash\n# One-line install (Linux / macOS)\ncurl -fsSL https://raw.githubusercontent.com/Ryvos/ryvos/main/install.sh | sh\nryvos init    # pick your LLM provider, paste an API key\nryvos         # start your AI coding assistant\n```\n\n---\n\n## Why Ryvos?\n\nMost AI coding assistants are built on TypeScript or Python runtimes that were never designed for autonomous, always-on operation. They're heavy, insecure, and fragile to deploy.\n\nRyvos is a complete reimagination — built in Rust from scratch as a true **autonomous AI agent runtime**:\n\n| | Typical AI assistants | **Ryvos** |\n|---|---|---|\n| **Language** | TypeScript / Python | **Rust** |\n| **Memory (idle)** | 200–500 MB | **15–30 MB** |\n| **Execution model** | Run until max_turns | **Goal-driven with Judge verdict** |\n| **Tool security** | None (arbitrary code) | **Constitutional AI safety + Docker sandboxing** |\n| **Dangerous command detection** | None | **9 built-in patterns (rm -rf, DROP TABLE, curl\\|bash…)** |\n| **Deployment** | npm/pip + runtime + Docker | **Single static binary** |\n| **MCP support** | Plugin/community | **Native (stdio + SSE/Streamable HTTP)** |\n| **Parallel tool execution** | Rare | **Built-in** |\n| **Multi-agent workflows** | Separate orchestration layer | **Built-in DAG engine + orchestrator** |\n| **Channel adapters** | Separate projects | **Built-in (Telegram, Discord, Slack, WhatsApp)** |\n| **HTTP Gateway** | Separate project | **Built-in with Web UI + RBAC** |\n\nIf you've used Claude Code, Aider, or Cursor and wanted something lighter, self-hosted, or with a proper security model — Ryvos is built for you.\n\n---\n\n## What is Ryvos?\n\nRyvos is an open-source, autonomous AI coding assistant and agent runtime you run on your own hardware. It connects to **18+ LLM providers** (Anthropic, OpenAI, Gemini, Azure, Cohere, Ollama, Groq, OpenRouter, Together, Fireworks, Cerebras, xAI, Mistral, Perplexity, DeepSeek, Bedrock, Claude Code, GitHub Copilot), executes tasks through **86+ sandboxed tools**, and reaches you on the channels you already use — Telegram, Discord, Slack, WhatsApp, Webhooks — plus a built-in Web UI and terminal interface.\n\nWritten in **Rust**. Ships as a **single binary**. Uses **15–30 MB of RAM**.\n\n---\n\n## Features\n\n### Goal-Driven Execution\n- **Goals with weighted success criteria** — define what \"done\" means with `OutputContains`, `OutputEquals`, `LlmJudge`, or `Custom` criteria, each with individual weights\n- **Constraints** — hard and soft limits on time, cost, safety, scope, and quality\n- **Two-level Judge** — Level 0 (deterministic fast-check) + LLM ConversationJudge that evaluates full conversation context\n- **Verdicts** — `Accept(confidence)`, `Retry(reason, hint)`, `Escalate(reason)`, or `Continue` — the agent keeps going until the goal is met or turns run out\n\n### Autonomous AI Agent\n- **ReAct agent loop** with tool use, reflexion, and streaming responses\n- **Parallel tool execution** — multiple tools run concurrently when independent\n- **18+ LLM providers** — Anthropic, OpenAI, Gemini, Azure, Cohere, Ollama, Groq, OpenRouter, Together, Fireworks, Cerebras, xAI, Mistral, Perplexity, DeepSeek, Bedrock, Claude Code, GitHub Copilot\n- **Session persistence** — SQLite-backed conversation history and memory across restarts\n- **Sub-agent spawning** — delegate tasks to child agents with stricter security\n- **Lifecycle hooks** — trigger shell commands on start, message, tool call, response, turn complete, tool error, session start/end\n- **Checkpoint / resume** — agent state persisted to SQLite after each turn; crashed runs resume automatically\n- **Decision tracking** — every tool call choice recorded with alternatives, confidence scores, and outcome (tokens, latency, success)\n- **Structured output validation** — heuristic repair (strip code fences, balance JSON braces, enforce max length) + optional LLM repair against expected schema\n\n### DAG Workflow Engine\n- **Graph execution** — define multi-step workflows as directed acyclic graphs of agent nodes\n- **Node types** — each node is an independent agent run with its own system prompt, tools, goal, and max turns\n- **Edge conditions** — `Always`, `OnSuccess`, `OnFailure`, `Conditional(expression)`, `LlmDecide(prompt)`\n- **Handoff context** — shared key-value store for passing data between nodes with JSON extraction\n- **Multi-agent orchestrator** — capability-based routing with `Parallel`, `Relay`, and `Broadcast` dispatch modes\n\n### Multi-Channel Inbox\n- **Telegram, Discord, Slack, WhatsApp** — talk to your AI assistant on the platforms you already use\n- **Per-channel DM policies** — allowlist, open, or disabled access control per channel\n- **HTTP/WebSocket Gateway** — Axum-based server with embedded Web UI for browser access\n- **Terminal UI** — full ratatui-based TUI with adaptive banner and streaming output\n- **Interactive REPL** — quick command-line usage\n- **Daemon mode** — always-on background service with `--gateway` flag\n- **Cron scheduler** — recurring tasks with cron expressions, persistent across restarts\n- **Heartbeat** — periodic proactive agent checks with smart suppression and alert routing\n\n### Security (Constitutional AI Safety)\n- **Constitutional self-learning safety** — the agent reasons about every action using 7 built-in principles\n- **No tool is ever blocked** — safety comes from understanding, not prohibition\n- **Safety Memory** — the agent learns from past mistakes via SafetyMemory corrective rules\n- **Dangerous pattern detection** — 9 built-in patterns trigger explicit constitutional reasoning\n- **Docker sandboxing** — optional container isolation with memory limits, network isolation, and timeouts\n- **Optional checkpoints** — configure `pause_before` for tools that should wait for human acknowledgment\n- **Budget enforcement** — monthly dollar limits with soft warnings and hard stops\n- **Guardian watchdog** — detects stalls, doom loops (same tool called repeatedly), and budget overruns; injects corrective hints\n\n### Observability\n- **JSONL runtime logging** — three-level logging (L1 run summary, L2 per-turn detail, L3 tool execution) — crash-resilient append-only format\n- **Decision journal** — SQLite-backed log of every tool call decision with alternatives and outcomes\n- **Scoped EventBus** — subscribe to filtered events by type, session, or node for monitoring and integrations\n- **Goal evaluation events** — stream `GoalEvaluated` and `JudgeVerdict` events to TUI, gateway, or custom subscribers\n- **Token usage tracking** — per-turn and per-run input/output token counts\n\n### Tools \u0026 Extensibility (86+ Built-in Tools)\n- **86+ built-in tools** — shell, file I/O, git, code analysis, network/HTTP, system, data transform, scheduling, database, sessions, memory, notifications, browser, and more across 18 categories\n- **MCP-native** — connect to any Model Context Protocol server (stdio + SSE/Streamable HTTP transports)\n- **Drop-in skills** — Lua/Rhai scripts in `~/.ryvos/skills/` with manifest-declared schemas and sandbox requirements\n- **Tool registry** — built-in tools + custom tools via MCP or skills\n- **Role-based API keys** — Viewer, Operator, Admin roles for gateway access\n- **Soul interview** — `ryvos soul` runs a 5-question personality interview that generates SOUL.md, shaping agent tone, proactivity, and operator context\n\n### Viking Memory\n- **Hierarchical context database** — L0/L1/L2 tiered loading with FTS search for fast, relevant context retrieval\n\n### Browser Automation\n- **5 browser tools** — navigate, screenshot, click, type, extract (powered by Chromium)\n\n### WhatsApp Channel\n- **Cloud API adapter** for WhatsApp Business — full bidirectional messaging\n\n### Budget System\n- **Monthly dollar limits** with configurable warn/hard-stop thresholds\n\n### Semantic Memory\n- **Embedding-based search** for long-term context retrieval across sessions\n\n### Constitutional AI Safety\n- **Self-learning safety** with 7 principles and SafetyMemory — the agent improves its safety behavior over time\n\n---\n\n## Quick Start\n\n### Install\n\n```bash\n# One-line install (Linux / macOS) — recommended\ncurl -fsSL https://raw.githubusercontent.com/Ryvos/ryvos/main/install.sh | sh\n\n# Pin a specific version\nRYVOS_VERSION=v0.6.5 curl -fsSL https://raw.githubusercontent.com/Ryvos/ryvos/main/install.sh | sh\n\n# Custom install directory\nRYVOS_INSTALL_DIR=/usr/local/bin curl -fsSL https://raw.githubusercontent.com/Ryvos/ryvos/main/install.sh | sh\n```\n\n\u003cdetails\u003e\n\u003csummary\u003eBuild from source (Rust 1.75+)\u003c/summary\u003e\n\n```bash\ncargo install --path .\n```\n\u003c/details\u003e\n\n\u003cdiv align=\"center\"\u003e\n\n\u003cimg src=\"docs/demo.gif\" alt=\"Ryvos demo — constitutional safety evaluates every action\" width=\"720\"\u003e\n\n*Constitutional safety evaluates every action with full audit logging*\n\n\u003c/div\u003e\n\n### Get Started\n\n```bash\n# Interactive setup — pick a provider, configure security, install service\nryvos init\n\n# Non-interactive setup (defaults to Ollama / qwen2.5:7b for local inference)\nryvos init -y --provider ollama --model-id qwen2.5:7b\n\n# Start your AI coding assistant\nryvos\n\n# Ask a quick question and exit\nryvos run \"Summarize the last 5 git commits in this repo\"\n\n# Launch the terminal UI\nryvos tui\n\n# Start the Web UI + HTTP/WebSocket gateway\nryvos serve\n\n# Always-on: Telegram + Discord + Slack + WhatsApp + gateway in one process\nryvos daemon --gateway\n\n# Check system health\nryvos doctor\n```\n\n### Uninstall\n\n```bash\nrm ~/.local/bin/ryvos\nrm -rf ~/.ryvos   # optional: remove config and data\n```\n\n### Shell Completions\n\n```bash\nryvos completions bash \u003e ~/.local/share/bash-completion/completions/ryvos  # bash\nryvos completions zsh \u003e ~/.zfunc/_ryvos                                    # zsh\nryvos completions fish \u003e ~/.config/fish/completions/ryvos.fish             # fish\n```\n\n### Commands\n\n| Command | Description |\n|---------|-------------|\n| `ryvos` | Interactive conversation (default) |\n| `ryvos run \u003cprompt\u003e` | Ask a question, get an answer, exit |\n| `ryvos tui` | Terminal UI with streaming output |\n| `ryvos serve` | Web UI + HTTP/WebSocket gateway |\n| `ryvos daemon` | Always-on assistant (Telegram, Discord, Slack, WhatsApp) |\n| `ryvos daemon --gateway` | Always-on + Web UI in one process |\n| `ryvos init` | Interactive setup wizard |\n| `ryvos init -y` | Non-interactive setup with defaults |\n| `ryvos soul` | Personalize your agent (5-question interview → SOUL.md) |\n| `ryvos config` | Print resolved configuration |\n| `ryvos doctor` | System health checks (API, workspace, DB, channels, cron, MCP, security) |\n| `ryvos health` | Tool health statistics |\n| `ryvos mcp list` | List configured MCP servers |\n| `ryvos mcp add \u003cname\u003e` | Add an MCP server |\n| `ryvos completions \u003cshell\u003e` | Generate shell completions (bash, zsh, fish) |\n\n---\n\n## Architecture\n\nRyvos is a Cargo workspace with 10 crates. Together they form a complete autonomous AI agent runtime — goal-driven LLM reasoning, DAG workflow orchestration, tool execution, security enforcement, persistent memory, multi-channel inbox, and observability — all in one binary.\n\n```\n┌─────────────────────────────────────────────────────┐\n│                     ryvos (CLI)                     │\n├──────────┬──────────┬───────────┬───────────────────┤\n│ ryvos-tui│  ryvos-  │  ryvos-   │  ryvos-channels   │\n│  (TUI)   │ gateway  │  agent    │(Telegram/Discord/  │\n│          │(HTTP/WS) │           │ Slack/WhatsApp)    │\n├──────────┴──────────┤           ├───────────────────┤\n│    ryvos-skills     │           │    ryvos-mcp      │\n│  (Lua/Rhai loader)  │           │  (MCP client)     │\n├─────────────────────┼───────────┼───────────────────┤\n│    ryvos-tools      │ ryvos-llm │  ryvos-memory     │\n│  (tool registry)    │(streaming │  (SQLite store)   │\n│                     │  client)  │                   │\n├─────────────────────┴───────────┴───────────────────┤\n│                   ryvos-core                        │\n│    (config, error types, event bus, security,       │\n│     goal system, traits, types)                     │\n└─────────────────────────────────────────────────────┘\n```\n\n| Crate | Purpose |\n|-------|---------|\n| `ryvos-core` | Config, error types, scoped event bus, security policy, goal system, traits |\n| `ryvos-llm` | LLM client abstraction with streaming support (18+ providers) |\n| `ryvos-tools` | Tool registry, 86+ built-in tools across 18 categories |\n| `ryvos-agent` | ReAct loop, SecurityGate, ApprovalBroker, Guardian watchdog, Judge, GoalEvaluator, OutputValidator, CheckpointStore, RunLogger, CronScheduler, GraphExecutor, MultiAgentOrchestrator |\n| `ryvos-memory` | SQLite-backed session and history storage |\n| `ryvos-gateway` | Axum HTTP/WS server, Web UI, role-based auth middleware |\n| `ryvos-channels` | Telegram, Discord, Slack, WhatsApp adapters with DM policy enforcement |\n| `ryvos-mcp` | MCP client (stdio + SSE transports) with sampling control |\n| `ryvos-skills` | Drop-in skill loader (Lua/Rhai) with manifest validation |\n| `ryvos-tui` | Terminal UI built on ratatui with adaptive banner |\n\n---\n\n## Security\n\nRyvos uses a **constitutional self-learning safety model** — the agent reasons about the appropriateness of every action using 7 built-in principles.\n\n**No tool is ever blocked.** Safety comes from understanding, not prohibition.\n\n### How It Works\n\n1. **Tool classification** — every tool has a security tier (T0 safe → T4 critical) for audit and context\n2. **Constitutional reasoning** — the agent evaluates each action against 7 principles: Preservation, Intent Match, Proportionality, Transparency, Boundaries, Secrets, Learning\n3. **Safety Memory** — the agent learns from past mistakes. SafetyMemory stores lessons as corrective rules that improve behavior over time\n4. **Full audit trail** — every tool call is logged with input, output, safety reasoning, and outcome\n\n### Additional Safety Layers\n\n- **Dangerous pattern detection** — 9 built-in patterns (rm -rf, DROP TABLE, curl|bash, etc.) trigger explicit constitutional reasoning\n- **Docker sandboxing** — optional isolated execution for file system and network operations\n- **Optional checkpoints** — configure `pause_before` for tools that should wait for human acknowledgment\n- **Budget enforcement** — monthly dollar limits with soft warnings and hard stops\n\n\u003e The old tier-based blocking system has been replaced. Tiers are retained for classification and backward compatibility, but they do not gate execution. See the [security documentation](https://ryvos.dev/docs/security/overview) for details.\n\n---\n\n## Configuration\n\nConfiguration lives in `~/.ryvos/config.toml` (created by `ryvos init`). You can also place a `ryvos.toml` in the current directory.\n\n```toml\n[agent]\nmax_turns = 25\nparallel_tools = true\nenable_self_eval = true\n\n[agent.checkpoint]\nenabled = true\n\n[agent.log]\nenabled = true\nlog_dir = \"~/.ryvos/logs\"\n\n[agent.guardian]\nstall_timeout_secs = 60\ndoom_loop_threshold = 5\nbudget_tokens = 100000\n\n[model]\nprovider = \"anthropic\"\nmodel_id = \"claude-sonnet-4-20250514\"\napi_key = \"${ANTHROPIC_API_KEY}\"\n\n# Local / self-hosted (no API key required):\n# provider = \"ollama\"\n# model_id = \"qwen2.5:7b\"\n\n[security]\nmode = \"constitutional\"       # constitutional | legacy-tier\npause_before = [\"shell_exec\"] # optional human checkpoints\nbudget_monthly_usd = 50.0\nbudget_warn_pct = 80\n\n[gateway]\nbind = \"127.0.0.1:18789\"\n\n[[gateway.api_keys]]\nname = \"web-ui\"\nkey = \"rk_...\"\nrole = \"operator\"    # viewer | operator | admin\n\n[channels.telegram]\nbot_token = \"${TELEGRAM_BOT_TOKEN}\"\ndm_policy = \"allowlist\"\nallowed_users = [123456789]\n\n[mcp.servers.filesystem]\ntransport = { type = \"stdio\", command = \"npx\", args = [\"-y\", \"@modelcontextprotocol/server-filesystem\", \"/tmp\"] }\n```\n\n---\n\n## Roadmap\n\n### Completed\n- [x] Goal-driven execution with weighted success criteria\n- [x] Two-level Judge system (deterministic + LLM)\n- [x] Decision tracking and failure journal\n- [x] Structured output validation and repair\n- [x] JSONL runtime logging (L1/L2/L3)\n- [x] Phase-aware context compaction\n- [x] Three-layer prompt composition\n- [x] Checkpoint / resume\n- [x] DAG workflow engine (graph execution)\n- [x] Multi-agent orchestrator with capability-based routing\n- [x] Scoped EventBus with filtered subscriptions\n- [x] Cron scheduler with persistent resume\n- [x] Guardian watchdog (stall, doom loop, budget detection)\n- [x] Multi-channel inbox (Telegram, Discord, Slack)\n- [x] HTTP/WebSocket gateway with Web UI\n- [x] Heartbeat system with smart suppression and alert routing\n- [x] WhatsApp channel adapter (shipped in v0.5.0)\n- [x] Browser control — navigate, click, extract, screenshot (shipped in v0.5.0)\n- [x] Ryvos Cloud — hosted assistant with managed sessions (in preview at [cloud.ryvos.dev](https://cloud.ryvos.dev))\n\n### Upcoming\n- [ ] Pre-built binaries (Windows, macOS, Linux) via GitHub Releases\n- [ ] `cargo install ryvos` from crates.io\n- [ ] Signal, iMessage, and Google Chat channel adapters\n- [ ] Voice mode — wake word detection + speech-to-text + TTS\n- [ ] Mobile companion apps (iOS, Android) via WebSocket\n- [ ] Live Canvas — real-time document/artifact editing in Web UI\n- [ ] SOC 2 compliance documentation\n- [ ] Signed \u0026 verified skill marketplace\n- [ ] MCP sampling support (server-initiated LLM calls)\n\n---\n\n## Acknowledgments \u0026 Inspirations\n\nRyvos stands on the shoulders of great projects:\n\n- [Claude Code](https://claude.ai/code) — Developer-first CLI patterns and ReAct loop design\n- [Aider](https://github.com/paul-gauthier/aider) — Lightweight coding assistant philosophy\n- [Aden Hive](https://github.com/aden-hive/hive) — Goal-driven graph execution and evolution loops\n- [OpenClaw](https://github.com/openclaw/openclaw) — Channel adapter architecture and skills marketplace model\n- [OpenViking](https://github.com/volcengine/OpenViking) — Hierarchical context database with L0/L1/L2 tiered loading\n- [Paperclip](https://github.com/paperclipai/paperclip) — Multi-agent fleet orchestration patterns\n- [Model Context Protocol](https://modelcontextprotocol.io) — Open standard for LLM tool integration\n\n## Contributing\n\nWe welcome contributions. See [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines.\n\n---\n\n## Get Help\n\n- [GitHub Issues](https://github.com/Ryvos/ryvos/issues) — bug reports and feature requests\n- [GitHub Discussions](https://github.com/Ryvos/ryvos/discussions) — questions and community\n\n---\n\n## License\n\n[MIT](LICENSE)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fryvos%2Fryvos","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fryvos%2Fryvos","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fryvos%2Fryvos/lists"}