agentic-flow
Advanced tools
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,
The First AI Agent Framework That Gets Smarter AND Faster Every Time It Runs
| Get Started | Core Features | Enterprise | Documentation |
|---|---|---|---|
| Quick Start | Agent Booster | Kubernetes GitOps | Agent List |
| Deployment Options | ReasoningBank | Billing System | MCP Tools |
| Model Optimization | Multi-Model Router | Deployment Patterns | Complete Docs |
| agentic-jujutsu |
Most AI coding agents are painfully slow and frustratingly forgetful. They wait 500ms between every code change. They repeat the same mistakes indefinitely. They cost $240/month for basic operations.
Agentic Flow changes everything:
Code Review Agent (100 reviews/day):
| Component | Description | Performance | Documentation |
|---|---|---|---|
| Agent Booster | Ultra-fast local code transformations via Rust/WASM (auto-detects edits) | 352x faster, $0 cost | Docs |
| AgentDB | State-of-the-art memory with causal reasoning, reflexion, and skill learning | p95 < 50ms, 80% hit rate | Docs |
| ReasoningBank | Persistent learning memory system with semantic search | 46% faster, 100% success | Docs |
| Multi-Model Router | Intelligent cost optimization across 100+ LLMs | 85-99% cost savings | Docs |
| QUIC Transport | Ultra-low latency agent communication via Rust/WASM QUIC protocol | 50-70% faster than TCP, 0-RTT | Docs |
| Federation Hub 🆕 | Ephemeral agents (5s-15min lifetime) with persistent cross-agent memory | Infinite scale, 0 waste | Docs |
| Swarm Optimization 🆕 | Self-learning parallel execution with AI topology selection | 3-5x speedup, auto-optimizes | Docs |
CLI Usage:
npx agentdb <command>)--optimize flagnpx agentic-flow federation start 🆕Programmatic: All components importable: agentic-flow/agentdb, agentic-flow/router, agentic-flow/reasoningbank, agentic-flow/agent-booster, agentic-flow/transport/quic
Get Started:
# CLI: AgentDB memory operations
npx agentdb reflexion store "session-1" "implement_auth" 0.95 true "Success!"
npx agentdb skill search "authentication" 10
npx agentdb causal query "" "code_quality" 0.8
npx agentdb learner run
# CLI: Auto-optimization (Agent Booster runs automatically on code edits)
npx agentic-flow --agent coder --task "Build a REST API" --optimize
# CLI: Federation Hub (ephemeral agents with persistent memory)
npx agentic-flow federation start # Start hub server
npx agentic-flow federation spawn # Spawn ephemeral agent
npx agentic-flow federation stats # View statistics
# CLI: Swarm Optimization (automatic parallel execution)
# Self-learning system recommends optimal topology (mesh, hierarchical, ring)
# Achieves 3-5x speedup with auto-optimization from learned patterns
# Programmatic: Import any component
import { ReflexionMemory, SkillLibrary, CausalMemoryGraph } from 'agentic-flow/agentdb';
import { ModelRouter } from 'agentic-flow/router';
import * as reasoningbank from 'agentic-flow/reasoningbank';
import { AgentBooster } from 'agentic-flow/agent-booster';
import { QuicTransport } from 'agentic-flow/transport/quic';
import { SwarmLearningOptimizer, autoSelectSwarmConfig } from 'agentic-flow/hooks/swarm-learning-optimizer';
Built on Claude Agent SDK by Anthropic, powered by Claude Flow (101 MCP tools), Flow Nexus (96 cloud tools), OpenRouter (100+ LLM models), Google Gemini (fast, cost-effective inference), Agentic Payments (payment authorization), and ONNX Runtime (free local CPU or GPU inference).
Production-ready Kubernetes operator powered by change-centric Jujutsu VCS (next-gen Git alternative):
# Install Kubernetes controller via Helm
helm repo add agentic-jujutsu https://agentic-jujutsu.io/helm
helm install agentic-jujutsu agentic-jujutsu/agentic-jujutsu-controller \
--set jujutsu.reconciler.interval=5s \
--set e2b.enabled=true
# Monitor GitOps reconciliation
kubectl get jjmanifests -A --watch
Key Features:
Architecture:
packages/k8s-controller/)JJManifest for Jujutsu repo syncUse Cases:
Documentation: Kubernetes Controller Guide
Native TypeScript billing system with 5 subscription tiers and 10 metered resources:
# CLI: Billing operations
npx ajj-billing subscription:create user123 professional monthly payment_method_123
npx ajj-billing usage:record sub_456 agent_hours 10.5
npx ajj-billing pricing:tiers
npx ajj-billing coupon:create LAUNCH25 percentage 25
# Programmatic API
import { BillingSystem } from 'agentic-flow/billing';
const billing = new BillingSystem({ enableMetering: true });
await billing.subscribe({ userId: 'user123', tier: 'professional', billingCycle: 'monthly' });
Subscription Tiers:
| Tier | Price | Agent Hours | API Requests | Deployments |
|---|---|---|---|---|
| Free | $0/mo | 10 hrs | 1,000 | 5 |
| Starter | $29/mo | 50 hrs | 10,000 | 25 |
| Professional | $99/mo | 200 hrs | 100,000 | 100 |
| Business | $299/mo | 1,000 hrs | 1,000,000 | 500 |
| Enterprise | Custom | Unlimited | Unlimited | Unlimited |
Metered Resources: Agent Hours, Deployments, API Requests, Storage (GB), Swarm Size, GPU Hours, Bandwidth (GB), Concurrent Jobs, Team Members, Custom Domains
Features:
Documentation: Economic System Guide
7 battle-tested deployment strategies scored 92-99/100 with performance benchmarks:
| Pattern | Score | Use Case | Best For |
|---|---|---|---|
| Rolling Update | 95/100 | General deployments | Zero-downtime updates |
| Blue-Green | 99/100 | Critical services | Instant rollback |
| Canary | 92/100 | Risk mitigation | Gradual rollout |
| A/B Testing | 94/100 | Feature validation | User testing |
| Shadow | 93/100 | Testing in production | Risk-free validation |
| Feature Toggle | 96/100 | Incremental releases | Dark launches |
| Progressive Delivery | 97/100 | Advanced scenarios | Metric-driven rollout |
Example: Canary Deployment
apiVersion: flagger.app/v1beta1
kind: Canary
metadata:
name: api-service-canary
spec:
targetRef:
apiVersion: apps/v1
kind: Deployment
name: api-service
progressDeadlineSeconds: 300
service:
port: 8080
analysis:
interval: 30s
threshold: 10
maxWeight: 50
stepWeight: 10
metrics:
- name: request-success-rate
thresholdRange:
min: 99
- name: request-duration
thresholdRange:
max: 500
Performance Benchmarks:
Documentation: Deployment Patterns Guide
High-performance Rust/NAPI bindings for change-centric version control:
# Install native package
npm install agentic-jujutsu
# Use in TypeScript/JavaScript
import { JJOperation, QuantumSigning } from 'agentic-jujutsu';
// Perform Jujutsu operations
const op = new JJOperation({
operation_type: 'Rebase',
target_revision: 'main@origin',
metadata: { commits: '5', conflicts: '0' }
});
await op.execute();
// Quantum-resistant signing (v2.2.0-alpha)
const signer = new QuantumSigning();
const signature = await signer.sign(data);
Features:
Platform Support:
darwin-arm64 (Apple Silicon)darwin-x64 (Intel Mac)linux-arm64-gnu (ARM Linux)linux-x64-gnu (x64 Linux)win32-arm64-msvc (ARM Windows)win32-x64-msvc (x64 Windows)linux-arm64-musl (Alpine ARM)⚠️ IMPORTANT: Quantum cryptography features are placeholder implementations in current release. Production quantum-resistant signing requires QUAG integration (planned for v2.3.0).
Documentation: agentic-jujutsu Package
HIPAA-compliant healthcare AI platform with patient consent management:
Key Features:
Consent Management Example:
import { DataSharingControls } from 'agentic-flow/consent';
const controls = new DataSharingControls();
// Create patient data sharing policy
await controls.createPolicy({
patientId: 'patient123',
allowedProviders: ['dr_smith', 'lab_abc'],
dataCategories: ['labs', 'medications', 'vitals'],
restrictions: [{
type: 'time_based',
description: 'Only share during business hours',
rules: { allowedHours: [9, 17] }
}],
active: true
});
// Check if data sharing is allowed
const result = controls.isDataSharingAllowed('patient123', 'dr_smith', 'labs');
// { allowed: true }
Use Cases:
Documentation: Healthcare AI Components
AgentDB-powered research platform for maternal health outcomes:
Key Features:
Example: Causal Inference
import { LeanAgenticIntegration } from 'agentic-flow/verification';
const integration = new LeanAgenticIntegration();
// Validate causal relationship
const result = await integration.validateCausalInference(
'Does prenatal care reduce preterm births?',
{ effectEstimate: -0.15, standardError: 0.03, randomized: false },
{
variables: [
{ name: 'prenatal_care', type: 'treatment', observed: true },
{ name: 'preterm_birth', type: 'outcome', observed: true },
{ name: 'maternal_age', type: 'confounder', observed: true }
],
relationships: [
{ from: 'prenatal_care', to: 'preterm_birth', type: 'direct' }
]
}
);
// Result: { effect: -0.15, pValue: 0.001, significant: true, confidence: [-0.21, -0.09] }
Statistical Methods:
Documentation: Maternal Health Platform
| Workflow | Traditional Agent | Agentic Flow | Improvement |
|---|---|---|---|
| Code Review (100/day) | 35s latency, $240/mo | 0.1s, $0/mo | 352x faster, 100% free |
| Migration (1000 files) | 5.87 min, $10 | 1 sec, $0 | 350x faster, $10 saved |
| Refactoring Pipeline | 70% success | 90% success | +46% execution speed |
| Autonomous Bug Fix | Repeats errors | Learns patterns | Zero supervision |
The only agent framework that gets faster AND smarter the more you use it.
# Global installation
npm install -g agentic-flow
# Or use directly with npx (no installation)
npx agentic-flow --help
# Set your API key
export ANTHROPIC_API_KEY=sk-ant-...
# Run locally with full 213 MCP tool access (Claude)
npx agentic-flow \
--agent researcher \
--task "Analyze microservices architecture trends in 2025"
# Run with OpenRouter for 99% cost savings
export OPENROUTER_API_KEY=sk-or-v1-...
npx agentic-flow \
--agent coder \
--task "Build a REST API with authentication" \
--model "meta-llama/llama-3.1-8b-instruct"
# Enable real-time streaming
npx agentic-flow \
--agent coder \
--task "Build a web scraper" \
--stream
# Build container
docker build -f deployment/Dockerfile -t agentic-flow .
# Run agent with Claude
docker run --rm \
-e ANTHROPIC_API_KEY=sk-ant-... \
agentic-flow \
--agent researcher \
--task "Analyze cloud patterns"
coder - Implementation specialist for writing clean, efficient codereviewer - Code review and quality assurancetester - Comprehensive testing with 90%+ coverageplanner - Strategic planning and task decompositionresearcher - Deep research and information gatheringbackend-dev - REST/GraphQL API developmentmobile-dev - React Native mobile appsml-developer - Machine learning model creationsystem-architect - System design and architecturecicd-engineer - CI/CD pipeline creationapi-docs - OpenAPI/Swagger documentationhierarchical-coordinator - Tree-based leadershipmesh-coordinator - Peer-to-peer coordinationadaptive-coordinator - Dynamic topology switchingswarm-memory-manager - Cross-agent memory syncpr-manager - Pull request lifecycle managementcode-review-swarm - Multi-agent code reviewissue-tracker - Intelligent issue managementrelease-manager - Automated release coordinationworkflow-automation - GitHub Actions specialistUse npx agentic-flow --list to see all 150+ agents
Automatically select the optimal model for any agent and task, balancing quality, cost, and speed based on your priorities.
# Let the optimizer choose (balanced quality vs cost)
npx agentic-flow --agent coder --task "Build REST API" --optimize
# Optimize for lowest cost
npx agentic-flow --agent coder --task "Simple function" --optimize --priority cost
# Optimize for highest quality
npx agentic-flow --agent reviewer --task "Security audit" --optimize --priority quality
# Set maximum budget ($0.001 per task)
npx agentic-flow --agent coder --task "Code cleanup" --optimize --max-cost 0.001
Tier 1: Flagship (premium quality)
Tier 2: Cost-Effective (2025 breakthrough models)
Tier 3: Balanced
Tier 4: Budget
Tier 5: Local/Privacy
Without Optimization (always using Claude Sonnet 4.5):
With Optimization (DeepSeek R1 for reviews):
Learn More:
# Agent execution with auto-optimization
npx agentic-flow --agent coder --task "Build REST API" --optimize
npx agentic-flow --agent coder --task "Fix bug" --provider openrouter --priority cost
# Billing operations (NEW: ajj-billing CLI)
npx ajj-billing subscription:create user123 professional monthly payment_method_123
npx ajj-billing subscription:status sub_456
npx ajj-billing usage:record sub_456 agent_hours 10.5
npx ajj-billing pricing:tiers
npx ajj-billing coupon:create LAUNCH25 percentage 25
npx ajj-billing help
# MCP server management (7 tools built-in)
npx agentic-flow mcp start # Start MCP server
npx agentic-flow mcp list # List 7 agentic-flow tools
npx agentic-flow mcp status # Check server status
# Agent management
npx agentic-flow --list # List all 79 agents
npx agentic-flow agent info coder # Get agent details
npx agentic-flow agent create # Create custom agent
Built-in CLIs:
External MCP Servers: claude-flow (101 tools), flow-nexus (96 tools), agentic-payments (10 tools)
NEW in v1.6.0: QUIC protocol support for ultra-fast agent communication, embedding agentic intelligence in the fabric of the internet.
QUIC (Quick UDP Internet Connections) is a UDP-based transport protocol offering 50-70% faster connections than traditional TCP, perfect for high-frequency agent coordination and real-time swarm communication. By leveraging QUIC's native internet-layer capabilities, agentic-flow embeds AI agent intelligence directly into the infrastructure of the web, enabling seamless, ultra-low latency coordination at internet scale.
| Feature | TCP/HTTP2 | QUIC | Improvement |
|---|---|---|---|
| Connection Setup | 3 round trips | 0-RTT (instant) | Instant reconnection |
| Latency | Baseline | 50-70% lower | 2x faster |
| Concurrent Streams | Head-of-line blocking | True multiplexing | 100+ streams |
| Network Changes | Connection drop | Migration support | Survives WiFi→cellular |
| Security | Optional TLS | Built-in TLS 1.3 | Always encrypted |
# Start QUIC server (default port 4433)
npx agentic-flow quic
# Custom configuration
npx agentic-flow quic --port 5000 --cert ./certs/cert.pem --key ./certs/key.pem
# Using environment variables
export QUIC_PORT=4433
export QUIC_CERT_PATH=./certs/cert.pem
export QUIC_KEY_PATH=./certs/key.pem
npx agentic-flow quic
# View QUIC options
npx agentic-flow quic --help
import { QuicTransport } from 'agentic-flow/transport/quic';
import { getQuicConfig } from 'agentic-flow/dist/config/quic.js';
// Create QUIC transport
const transport = new QuicTransport({
host: 'localhost',
port: 4433,
maxConcurrentStreams: 100 // 100+ parallel agent messages
});
// Connect to QUIC server
await transport.connect();
// Send agent tasks with minimal latency
await transport.send({
type: 'task',
agent: 'coder',
data: { action: 'refactor', files: [...] }
});
// Get connection stats
const stats = transport.getStats();
console.log(`RTT: ${stats.rttMs}ms, Active streams: ${stats.activeStreams}`);
// Graceful shutdown
await transport.close();
Perfect for:
Real-World Example:
// Coordinate 10 agents processing 1000 files
const swarm = await createSwarm({ topology: 'mesh', transport: 'quic' });
// QUIC enables instant task distribution
for (const file of files) {
// 0-RTT: No connection overhead between tasks
await swarm.assignTask({ type: 'analyze', file });
}
// Result: 50-70% faster than TCP-based coordination
| Variable | Description | Default |
|---|---|---|
QUIC_PORT | Server port | 4433 |
QUIC_CERT_PATH | TLS certificate path | ./certs/cert.pem |
QUIC_KEY_PATH | TLS private key path | ./certs/key.pem |
Learn More: QUIC Documentation
import { ModelRouter } from 'agentic-flow/router';
const router = new ModelRouter();
const response = await router.chat({
model: 'auto', priority: 'cost', // Auto-select cheapest model
messages: [{ role: 'user', content: 'Your prompt' }]
});
console.log(`Cost: $${response.metadata.cost}, Model: ${response.metadata.model}`);
import * as reasoningbank from 'agentic-flow/reasoningbank';
await reasoningbank.initialize();
await reasoningbank.storeMemory('pattern_name', 'pattern_value', { namespace: 'api' });
const results = await reasoningbank.queryMemories('search query', { namespace: 'api' });
Automatic: Detects code editing tasks and applies 352x speedup with $0 cost
Manual: import { AgentBooster } from 'agentic-flow/agent-booster' for direct control
Providers: Anthropic (Claude), OpenRouter (100+ models), Gemini (fast), ONNX (free local)
Agentic Flow integrates with four MCP servers providing 213 tools total:
| Category | Tools | Capabilities |
|---|---|---|
| Swarm Management | 12 | Initialize, spawn, coordinate multi-agent swarms |
| Memory & Storage | 10 | Persistent memory with TTL and namespaces |
| Neural Networks | 12 | Training, inference, WASM-accelerated computation |
| GitHub Integration | 8 | PR management, code review, repository analysis |
| Performance | 11 | Metrics, bottleneck detection, optimization |
| Workflow Automation | 9 | Task orchestration, CI/CD integration |
| Dynamic Agents | 7 | Runtime agent creation and coordination |
| System Utilities | 8 | Health checks, diagnostics, feature detection |
| Category | Tools | Capabilities |
|---|---|---|
| ☁️ E2B Sandboxes | 12 | Isolated execution environments (Node, Python, React) |
| ☁️ Distributed Swarms | 8 | Cloud-based multi-agent deployment |
| ☁️ Neural Training | 10 | Distributed model training clusters |
| ☁️ Workflows | 9 | Event-driven automation with message queues |
| ☁️ Templates | 8 | Pre-built project templates and marketplace |
| ☁️ User Management | 7 | Authentication, profiles, credit management |
Benefits:
Benefits:
Benefits:
Benefits:
| Metric | Result |
|---|---|
| Cold Start | <2s (including MCP initialization) |
| Warm Start | <500ms (cached MCP servers) |
| Agent Spawn | 150+ agents loaded in <2s |
| Tool Discovery | 213 tools accessible in <1s |
| Memory Footprint | 100-200MB per agent process |
| Concurrent Agents | 10+ on t3.small, 100+ on c6a.xlarge |
| Token Efficiency | 32% reduction via swarm coordination |
| Resource | Description | Link |
|---|---|---|
| NPM Package | Install and usage | npmjs.com/package/agentic-flow |
| Agent Booster | Local code editing engine | Agent Booster Docs |
| ReasoningBank | Learning memory system | ReasoningBank Docs |
| Model Router | Cost optimization system | Router Docs |
| MCP Tools | Complete tool reference | MCP Documentation |
| Integration | Description | Link |
|---|---|---|
| Claude Agent SDK | Official Anthropic SDK | docs.claude.com/en/api/agent-sdk |
| Claude Flow | 101 MCP tools | github.com/ruvnet/claude-flow |
| Flow Nexus | 96 cloud tools | github.com/ruvnet/flow-nexus |
| OpenRouter | 100+ LLM models | openrouter.ai |
| Agentic Payments | Payment authorization | Payments Docs |
| ONNX Runtime | Free local inference | onnxruntime.ai |
| Package | Version | Purpose |
|---|---|---|
@anthropic-ai/claude-agent-sdk | ^1.0.0 | Claude agent runtime |
claude-flow | latest | MCP server with 101 tools |
flow-nexus | latest | Cloud platform (96 tools) |
agentic-payments | latest | Payment authorization (10 tools) |
We welcome contributions! Please see CONTRIBUTING.md for guidelines.
git checkout -b feature/amazing-featurenpm testgit commit -m "feat: add amazing feature"git push origin feature/amazing-featureMIT License - see LICENSE for details.
Built with:
Deploy ephemeral AI agents in seconds. Scale to thousands. Pay only for what you use. 🚀
npx agentic-flow --agent researcher --task "Your task here"
FAQs
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,
The npm package agentic-flow receives a total of 0 weekly downloads. As such, agentic-flow popularity was classified as not popular.
We found that agentic-flow demonstrated a healthy version release cadence and project activity because the last version was released less than a year ago. It has 1 open source maintainer collaborating on the project.
Did you know?
Socket for GitHub automatically highlights issues in each pull request and monitors the health of all your open source dependencies. Discover the contents of your packages and block harmful activity before you install or update your dependencies.
Company News
Socket won two 2026 Reppy Awards from RepVue, ranking in the top 5% of all sales orgs. AE Alexandra Lister shares what it's like to grow a sales career here.
Security News
NIST will stop enriching most CVEs under a new risk-based model, narrowing the NVD's scope as vulnerability submissions continue to surge.
Company News
/Security News
Socket is an initial recipient of OpenAI's Cybersecurity Grant Program, which commits $10M in API credits to defenders securing open source software.