agentic-flow
Production-ready AI agent orchestration platform with 66 specialized agents, 213 MCP tools, ReasoningBank learning memory, and autonomous multi-agent swarms. Built by @ruvnet with Claude Agent SDK, ne
Description
Production-ready AI agent orchestration platform with 66 specialized agents, 213 MCP tools, ReasoningBank learning memory, and autonomous multi-agent swarms. Built by @ruvnet with Claude Agent SDK, neural networks, memory persistence, GitHub integration,
Release History
| Version | Changes | Urgency | Date |
|---|---|---|---|
| 2.0.7 | Imported from npm (2.0.7) | Low | 4/21/2026 |
| v2.3.6 | Release v2.3.6 | Low | 11/24/2025 |
| v2.3.5 | Release v2.3.5 | Low | 11/24/2025 |
| v2.3.4 | Release v2.3.4 | Low | 11/16/2025 |
| v2.3.3 | Release v2.3.3 | Low | 11/10/2025 |
| v2.3.2 | ## v2.3.2 - Documentation Update Updated README to reflect current features: - ✅ Removed "(Coming Soon)" entries - ✅ Updated v2.3 quantum features section - ✅ Added v2.3.1 validation improvements - ✅ Clarified evolution timeline No code changes - documentation only. **Install:** ```bash npm install agentic-jujutsu@2.3.2 ``` **Previous Release:** v2.3.1 - Validation fixes for ReasoningBank | Low | 11/10/2025 |
| v2.3.1 | # v2.3.1 - Validation Fixes Patch release addressing three validation gaps in the ReasoningBank trajectory management system. ## 🔧 Fixes ### Score Validation - ✅ Reject scores outside 0.0-1.0 range - ✅ Reject NaN and Infinity values - ✅ Proper error messages for invalid scores ### State Validation - ✅ Require at least one operation before finalization - ✅ Prevent empty trajectories from being stored ### Input Validation - ✅ Reject empty or whitespace-only task descriptions - ✅ Enforce max | Low | 11/10/2025 |
| v2.2.0 | Release v2.2.0 | Low | 11/10/2025 |
| v2.1.1 | Release v2.1.1 | Low | 11/10/2025 |
| v2.1.0 | Release v2.1.0 | Low | 11/10/2025 |
| v2.0.3 | Release v2.0.3 | Low | 11/10/2025 |
| v2.0.2 | Release v2.0.2 | Low | 11/10/2025 |
| v2.0.1 | Release v2.0.1 | Low | 11/10/2025 |
| v2.0.0 | Release v2.0.0 | Low | 11/10/2025 |
| v1.10.0 | # Release Notes - v1.10.0 **Release Date:** 2025-11-06 **Codename:** "Performance Breakthrough" **Branch:** `feature/http2-http3-websocket` → `main` --- ## 🎯 Overview Version 1.10.0 is a **major performance release** introducing enterprise-grade multi-protocol proxy support with **60% latency reduction** and **350% throughput increase**. This release includes comprehensive security features, advanced performance optimizations, and production-ready implementations. --- ## 🚀 Major Features | Low | 11/7/2025 |
| v1.9.4 | ## 🚀 Enterprise Provider Fallback & Dynamic Switching Production-grade provider fallback for long-running AI agents with automatic failover, circuit breaker, health monitoring, cost optimization, and crash recovery. ### New Core Classes #### `ProviderManager` (src/core/provider-manager.ts) Intelligent multi-provider management with automatic failover - **4 fallback strategies**: priority, cost-optimized, performance-optimized, round-robin - **Circuit breaker** prevents cascading failures wit | Low | 11/6/2025 |
| v1.9.3 | ## 🎉 Gemini Provider Now Fully Functional Three critical bugs have been fixed in v1.9.3, making the Gemini provider production-ready with complete streaming support. ### Fixed **1. Model Selection Bug** (cli-proxy.ts, anthropic-to-gemini.ts) - **Issue**: Proxy incorrectly used `COMPLETION_MODEL` environment variable containing `claude-sonnet-4-5-20250929` instead of Gemini model - **Fix**: Ignore `COMPLETION_MODEL` for Gemini proxy, always default to `gemini-2.0-flash-exp` - **Impact**: Gemi | Low | 11/6/2025 |
| v1.9.2 | ## 🔍 Gemini Provider Validation Release This release focuses on comprehensive testing and documentation of the Gemini provider integration. ### 🐛 Issues Documented - **Issue #51**: Gemini provider empty response bug - ✅ Proxy initialization works correctly - ✅ Request routing successful - ❌ Response conversion needs debugging - Comprehensive investigation findings included - **Issue #50**: Config wizard multi-provider support - Request to add GOOGLE_GEMINI_API_KEY prompt - Requ | Low | 11/6/2025 |
| v1.7.0 | # agentic-flow v1.7.0 - AgentDB Integration & Memory Optimization **Release Date**: 2025-01-24 **Status**: ✅ Ready for Release **Backwards Compatibility**: 100% Compatible --- ## 🎉 What's New ### Major Features #### 1. AgentDB Integration (Issue #34) - ✅ **Proper Dependency**: Integrated AgentDB v1.3.9 as npm dependency - ✅ **29 MCP Tools**: Full Claude Desktop support via Model Context Protocol - ✅ **Code Reduction**: Removed 400KB of duplicated embedded code - ✅ **Automatic Updates**: Ge | Low | 10/24/2025 |
| agentdb-v1.0.0 | ## agentdb v1.0.0 ### 🚀 Initial Release Ultra-fast agent memory and vector database with ReasoningBank for AI agents. Built on SQLite with QUIC sync. From ruv.io - Advanced AI Infrastructure. ### Key Features - ⚡ Dual backend support (Native better-sqlite3 + WASM sql.js) - 🧠 6 Advanced Learning Plugins (Federated, Curriculum, Active, Adversarial, NAS, Multi-Task) - 🔍 HNSW vector indexing for fast similarity search - 📊 Product & Scalar quantization for memory efficiency - 🔄 QUIC-based s | Low | 10/18/2025 |
| v1.6.4 | # 🚀 agentic-flow v1.6.4 - QUIC Transport Production Ready ## Overview Complete QUIC transport implementation with validated performance metrics. All features 100% complete and production-ready. ## ✨ New Features ### QUIC Transport - 100% Complete - ✅ **UDP Socket Integration** - Full packet bridge layer with WASM - ✅ **QUIC Handshake Protocol** - Complete state machine implementation - ✅ **Performance Validation** - All claims verified with benchmarks - ✅ **Docker Validation** - 12/12 tests | Low | 10/17/2025 |
| v1.3.0 | # Changelog - v1.3.0 ## Release Date: October 7, 2025 ## 🎉 Major Features ### Tool Emulation Architecture (Phase 2) Complete implementation of tool emulation system for models without native function calling support. **Key Features:** - ✅ Automatic model capability detection - ✅ ReAct and Prompt-based emulation strategies - ✅ User-facing emulation messages at 3 levels - ✅ Zero breaking changes - 100% backward compatible - ✅ 15/15 regression tests passing **Supported Models:** - Native tool | Low | 10/7/2025 |
| v1.2.7 | ## 🚀 What's New in v1.2.7 ### Auto-Enabled MCP Tools All MCP servers are now enabled by default, providing immediate access to 272 powerful tools without configuration! **MCP Tools Included:** - 🔧 **claude-flow-sdk**: 9 in-SDK tools - 🌊 **claude-flow**: 101 orchestration tools - 🔮 **flow-nexus**: 162 platform tools - 💳 **agentic-payments**: 9 payment tools - **Total: 272 tools ready to use!** ### Key Changes - ✅ Switched from opt-in to opt-out MCP configuration - ✅ All MCP servers load a | Low | 10/7/2025 |
| v1.1.14 | ## 🎉 Major Fix: OpenRouter Proxy Now Working! ### Critical Bug Fixed Fixed TypeError on `anthropicReq.system` field that was causing 100% failure rate for OpenRouter requests. ### Success Rate: 80% (8/10 models) **Working Models:** - ✅ OpenAI GPT-4o-mini (99% cost savings vs Claude!) - ✅ OpenAI GPT-3.5-turbo - ✅ Meta Llama 3.1 8B - ✅ Anthropic Claude 3.5 Sonnet (via OpenRouter) - ✅ Mistral 7B - ✅ Google Gemini 2.0 Flash - ✅ xAI Grok 4 Fast (#1 most popular OpenRouter model!) - ✅ GLM 4.6 - ✅ | Low | 10/5/2025 |
| v1.1.14-beta.1 | ## 🎉 Major Fix: OpenRouter Proxy Now Working! ### Critical Bug Fixed Fixed TypeError on `anthropicReq.system` field that was causing 100% failure rate for OpenRouter requests. ### Success Rate: 80% (8/10 models) **Working Models:** - ✅ OpenAI GPT-4o-mini (99% cost savings vs Claude!) - ✅ OpenAI GPT-3.5-turbo - ✅ Meta Llama 3.1 8B - ✅ Anthropic Claude 3.5 Sonnet (via OpenRouter) - ✅ Mistral 7B - ✅ Google Gemini 2.0 Flash - ✅ xAI Grok 4 Fast (#1 most popular OpenRouter model!) - ✅ GLM 4.6 - ✅ | Low | 10/5/2025 |
Dependencies & License Audit
Loading dependencies...
Similar Packages
claude-container🐳 Run Claude Code safely in isolated Docker containers with persistent projects and easy setup on macOS using Justfile automation.master@2026-04-21
crewformBuild your AI team with Crewform. Orchestrate specialized, autonomous agents to collaborate on complex tasks and connect outputs to your stack. — AI Orchestration for Everyonev1.8.2
docsDocumentation for the Strands Agents SDK. A model-driven approach to building AI agents in just a few lines of code. v0.1.0