Manus
General Autonomous Agents
- Fully autonomous agent in a cloud sandbox
- Breaks goals into steps and executes them
- Web research, code execution and file output
- 'My Computer' desktop environment
AI Agents & Automation (123)
123 free ai agents & automation tools and 3 more — pricing tier and real capabilities on every entry. No ads, no sponsored placement.
AllGeneral Autonomous AgentsWorkflow AutomationAgent Frameworks (Developers)Real-Time Voice AgentsBrowser & Computer-Use AgentsMCP EcosystemAgent Memory & RAG-as-a-Service
freemium
Perplexity Comet
General Autonomous Agents
- AI-native browser with a built-in agent
- Automates browsing, research and tasks
- Routes subtasks to the best model
- Cited answers as you browse
Genspark
General Autonomous Agents
- 'Super agent' that plans and executes end-to-end
- Generates sheets, slides and even phone calls
- Mixes multiple models and tools
- Free daily credits
Zhipu AutoGLM
General Autonomous Agents
- Free foundation-agent system for autonomous GUI control (web + Android)
- Voice-to-action: controls entire web/phone UI from a spoken instruction
- AutoGLM Rumination adds deep-research style multi-step task execution
Coze Space
General Autonomous Agents
- ByteDance's general-purpose office agent that breaks tasks into sub-tasks and drives a browser/code editor autonomously
- Outputs deliverables as web pages, PPTs or Lark docs
- Part of the Coze suite (Space/Studio/Loop/Eino) with an open-source Coze Studio component
MiniMax Agent
General Autonomous Agents
- General-purpose autonomous agent from MiniMax, separate from its Hailuo video product
- Built on MiniMax's M3-series multimodal agentic models
- Free daily credits; paid credit plans for heavier use
Flowith
General Autonomous Agents
- Infinite-canvas workspace where every prompt/output is a branchable, reusable node
- Agent Neo: autonomous agent that runs long tasks in the background 24/7
- Free Starter plan with one-time credits granting access to frontier models (Opus, GPT, Gemini) and Agent Neo
Convergence Proxy
General Autonomous Agents
- Free daily session quota; Pro lifts it to unlimited and adds parallel runs
- Open-weights Proxy Lite version available on GitHub for self-hosting
- Learns and adapts to user preferences across repeated web-automation tasks
Skywork AI
General Autonomous Agents
- Five specialized agents for docs, sheets, slides, podcasts and web content in one workspace
- DeepResearch-powered output generation across formats
- Free tier available alongside paid workspace plans
Ninja AI (NinjaTech)
General Autonomous Agents
- SuperNinja: autonomous agent running on its own dedicated VM for coding, research, website building
- Bundles multiple frontier models behind one subscription with 'Inference Level Optimization'
- Single agent spans coding, document analysis, and content generation tasks
HyperWrite AI Agent
General Autonomous Agents
- Browser-native personal agent that books, emails, and researches inside your existing tabs
- Free tier confirmed live plus paid upgrade for higher-volume agent tasks
- Long-running writing-assistant product line (from OthersideAI) now extended into full agentic tasks
- Open-source long-horizon SuperAgent harness that researches, codes and creates
- Sub-agents, sandboxed execution, memory and skills
- Model-agnostic; works with DeepSeek, OpenAI-compatible APIs
- MIT-licensed, self-hosted
- MIT-licensed personal AI agent running on your own hardware with a local gateway
- Connects to 20+ chat platforms including WhatsApp, Telegram, Slack and iMessage
- Swap in hosted or local models via plugins; no paid tier or token
- MIT self-improving agent by Nous Research that writes skills from experience
- Terminal UI plus Telegram, Discord, Slack and WhatsApp gateways
- Built-in scheduler, sub-agents and memory; runs on a cheap VPS
- Open-source agent platform (formerly Suna) that runs specialist agents on isolated cloud computers
- Agents produce finished deliverables such as reports and code and return them for human approval
- Free to self-host; managed cloud is paid
- Works with your own LLM provider keys
- Open-source general agent framework built as a free alternative to Manus
- Runs tasks with tools such as browser automation, code execution and file handling
- Works with any LLM API you supply, including local models
- MIT-style open code you can run locally at no cost
- Fully local autonomous agent that browses, codes and plans without cloud APIs
- Runs on local LLMs via Ollama or LM Studio, so there are no usage fees
- Voice-enabled task interface and multi-agent routing
- Free and open source
- Agent framework that gives the agent a full Linux desktop and browser to work in
- Multi-agent delegation, plugins and skills, with over 100 community plugins
- Project workspaces with isolated files, secrets and model choices
- Free and open source; bring your own model keys or use local models
- Lets an LLM run code locally to do tasks on your computer, in a terminal chat
- Works with open models such as Kimi and GLM through any compatible API
- Free and open source with no account needed
- Large community and steady releases
- Ultra-light self-hosted personal agent with memory, tools and cron scheduling
- Chats through Telegram, Discord, Slack, WeChat, email and Feishu
- MCP servers, web search, shell and file access
- MIT licensed; bring your own model
- Open-source agent that plans tasks, runs tools and builds long-term memory
- Runs in WeChat, Feishu, DingTalk, WeCom, QQ, Telegram, Slack, Discord and a web console
- Skills marketplace and a self-curated markdown knowledge base
- MIT licensed, bring your own model key
- Open-source platform for building and running continuous AI agents
- Low-code builder for agent workflows
- Self-host free
- One of the most starred AI repos
Zapier
Workflow Automation
- Connect 8,000+ apps with AI agents
- Natural-language automation builder
- AI steps, chatbots and tables
- Free tier for basic Zaps
n8n
Workflow Automation
- Open-source, self-hostable automation
- Visual AI-agent and LLM nodes
- Full code when you need it
- Free to run yourself
Make
Workflow Automation
- Visual drag-and-drop automation
- AI modules and agent scenarios
- 1,000+ app integrations
- Generous free tier
Gumloop
Workflow Automation
- No-code canvas for AI workflows
- Web scraping, extraction and enrichment
- Shareable automation templates
- Free plan to start
Coze
Workflow Automation
- No-code drag-and-drop bot/agent builder from ByteDance, distinct from Doubao's consumer chat app
- 60+ built-in plugins (search, travel, productivity) wired into published bots
- One-click publish to Telegram, Discord, Slack or your own site
Activepieces
Workflow Automation
- MIT-licensed, free-forever self-hosted Community Edition with unlimited runs/users/flows
- 700+ integrations plus AI-agent building blocks
- Cloud Free plan needs no credit card, includes unlimited flows with daily credit resets
Windmill
Workflow Automation
- Open-source, self-hostable with unlimited executions on the free tier
- Turns scripts (Python/TS/Go/Bash/SQL) into flows and full internal apps
- Kubernetes/Docker/Fargate deployable with a hybrid seat+compute enterprise pricing model
Pipedream
Workflow Automation
- Free tier: 300 credits/month, 3 active workflows, 3 connected accounts, no card required
- Mixes visual workflow building with full custom code steps (Node/Python)
- 2,000+ pre-built API integrations with fast event-driven triggers
Dify
Workflow Automation
- Open-source Community Edition, free self-deploy via Docker
- Cloud Sandbox plan: free with 200 message credits, 5 apps, 50 knowledge docs
- Visual builder combining agentic workflows with built-in RAG knowledge bases
Langflow
Workflow Automation
- Open source with 138k GitHub stars, free desktop app and free cloud account
- Drag-and-drop visual builder for agents and RAG pipelines on top of LangChain primitives
- Deep integrations across major LLMs, vector DBs and Google Cloud/Slack/MongoDB
Vellum
Workflow Automation
- Free builder tier with hosted agent apps, no card required
- Prompt-engineering playground for side-by-side multi-model comparison
- Built-in evaluations framework with test banks and custom metrics for LLM apps
Stack AI
Workflow Automation
- Free plan: 500 monthly runs, 2 projects, 1 seat, community Discord support
- No-code drag-and-drop builder aimed at compliant/regulated enterprise deployments
- SOC 2, HIPAA and GDPR compliance options at the enterprise tier
Botpress
Workflow Automation
- Free pay-as-you-go plan with a monthly message quota and AI credit
- Visual conversation-flow studio purpose-built for LLM-powered support/sales bots
- May 2026 pricing update added unlimited bots and free AI spend on new workspaces
Chatbase
Workflow Automation
- Free plan: 50 message credits/month, 1 AI agent, 1 workspace member
- Omnichannel deployment across chat, email, voice, WhatsApp and Slack from one trained agent
- Serves 10,000+ businesses for customer-support agent deployment
Trigger.dev
Workflow Automation
- Open source (Apache 2.0) with a genuine free tier and unlimited tasks
- Purpose-built for long-running, failure-resilient tasks (ideal for multi-step AI agent jobs)
- No server/timeout management — infra fully handled, pay per compute-second
Voiceflow
Workflow Automation
- Visual design canvas for building both voice and chat AI agents from one flow
- Multi-client/agency workspace mode with white-labeling for agencies
- Deployable across channels with real-time analytics and team collaboration
- Describe an app in plain language and Opal builds a shareable multi-step AI workflow
- Agent step for autonomous multi-step workflows and automated runs
- Chains prompts, Gemini/Veo/Imagen models and tools visually
- Available in 160+ countries, also inside the Gemini app as Gems
- Drag-and-drop builder for chatbots, agents and RAG flows
- Self-host free with Docker or npm, with many model and vector store integrations
- Agentflow for multi-agent orchestration
- Embeddable chat widget and API output
- Visual canvas for building, deploying and monitoring AI agents and workflows
- Open source and self-hostable
- Copilot that helps assemble workflows from natural language
- Integrations with common tools and knowledge bases
- Builds AI bots for WeChat, QQ, Discord, Slack, Telegram and other chat platforms
- Plugs into Dify, n8n, Coze and other workflow back ends
- Plugin system and web admin panel
- Free and open source, self-hosted
- Open-source version of ByteDance's Coze agent builder with visual workflows
- Plugins, knowledge bases, databases and memory for agents
- Apache 2.0 licensed, self-hosted with Docker
- Connects to OpenAI and other model providers
- Open-source platform for building LLM workflows, RAG and multi-agent apps
- Strong document parsing with OCR, tables and layout analysis
- Loops, parallelism and human-in-the-loop steps
- Apache 2.0, self-hosted
- Chrome-based AI automation for scraping, filling forms and moving data between apps
- Free plan includes a monthly credit allowance
- Playbooks you can build in plain language
- Integrates with Google Sheets, Notion and CRMs
LangGraph
Agent Frameworks (Developers)
- Build stateful, multi-agent apps as graphs
- Human-in-the-loop and durable execution
- Works with any LLM
- Open-source with a hosted platform
CrewAI
Agent Frameworks (Developers)
- Role-based multi-agent 'crews'
- Simple Python API for collaboration
- Tasks, tools and flows
- Open-source core
OpenAI Agents SDK
Agent Frameworks (Developers)
- Lightweight agent orchestration from OpenAI
- Agent handoffs, guardrails and tracing
- Tool and function calling built in
- Open-source, pay only for model usage
Microsoft AutoGen
Agent Frameworks (Developers)
- Multi-agent conversation framework
- Event-driven, async agent design
- Studio UI for prototyping
- Fully open-source
LlamaIndex
Agent Frameworks (Developers)
- Leading framework for RAG and data agents
- Connect LLMs to your documents & APIs
- Agentic document workflows
- Open-source with a hosted cloud
Google Agent Development Kit (ADK)
Agent Frameworks (Developers)
- Open-source Python/Java framework from Google for building multi-agent systems
- Native integration with Vertex AI Agent Engine and Gemini models
- Model-agnostic — works with non-Google LLMs via LiteLLM
Pydantic AI
Agent Frameworks (Developers)
- Type-safe Python agent framework from the Pydantic team, validated structured outputs
- Model-agnostic (OpenAI, Anthropic, Gemini, Groq, Mistral, local)
- Built-in dependency injection and streaming; pairs with Pydantic Logfire for observability
Mastra
Agent Frameworks (Developers)
- Open-source TypeScript framework (Apache 2.0) for agents, workflows and RAG
- Drops directly into existing React/Next.js apps or runs standalone
- Built-in workflow engine with suspend/resume and human-in-the-loop steps
Agno
Agent Frameworks (Developers)
- Open-source (Apache-2.0) Python framework, 41.7k GitHub stars
- AgentOS: FastAPI-based production runtime for deploying agents
- Control-plane UI for monitoring live agent systems across clouds
smolagents
Agent Frameworks (Developers)
- Extremely minimal open-source library (~1,000 lines) from Hugging Face
- CodeAgent paradigm: agents write actions as executable code, not JSON
- Model-agnostic and modality-agnostic (text, vision, audio) with sandboxed execution via E2B/Docker/Modal
AWS Strands Agents
Agent Frameworks (Developers)
- Open-source (6,800+ stars) Python and TypeScript SDK from AWS
- Steering handlers/hooks that catch agent mistakes before execution
- Native Bedrock and AWS AgentCore integration, plus any-LLM support
DSPy
Agent Frameworks (Developers)
- Open-source (MIT) framework from Stanford NLP, 37k+ GitHub stars
- Compiles/optimizes prompts automatically against metrics instead of manual prompt tuning
- Production use at Databricks, Shopify, Dropbox, AWS; Shopify reports ~550x cost reduction
- Unified open-source framework for building and orchestrating multi-agent systems in Python and .NET
- Successor merging Semantic Kernel and AutoGen ideas
- Graph workflows, memory and tool support
- Free, MIT-licensed
- Secure, fast runtime for executing untrusted AI-generated code
- SDKs and a self-hostable server
- Container and microVM isolation options
- Apache-licensed open source
- Agent framework built on Qwen 3+ with function calling, MCP and code interpreter
- Ships Browser Assistant and RAG examples
- Free and self-hostable
- Works with Qwen served locally or via DashScope
- Open-source framework for AI apps in JavaScript, Go, Dart and Python
- Built-in Developer UI for tracing and testing flows
- Model-agnostic plugins for Gemini, OpenAI, Anthropic, Ollama
- Free; deploy anywhere
- MIT-licensed Python and TypeScript SDKs exposing the agent loop that powers Claude Code
- Built-in tools for files, shell and MCP with custom tool support
- Bring an Anthropic API key; the SDK itself costs nothing
- MIT SDK for integrating LLMs into C#, Python and Java apps
- Plugins, planners and memory connectors
- Works with OpenAI, Azure and local models
- MIT-licensed framework of model, tool and retrieval integrations for agents
- Python and JavaScript versions
- Pairs with LangGraph and LangSmith (separate free tier)
- Batteries-included agent harness with planning, sub-agents and a virtual file system
- Built on LangGraph, model-agnostic
- Open source
- Apache-2.0 framework for context-engineered, production RAG and agent pipelines
- Modular components with retrievers, generators and tool calling
- Integrates most vector stores and model providers
- TypeScript toolkit for streaming text, tool calls and agents across many model providers
- React/Next/Vue/Svelte hooks for chat UIs
- Open source
- Open-source TypeScript agent framework with memory, tools and sub-agents
- VoltOps console for tracing (free tier)
- Provider-agnostic
- Open-source multi-agent framework focused on scaling agent societies and role-playing
- Data generation and simulation tooling
- Apache-licensed
- Framework for building and deploying stateful AI agents on Cloudflare Workers
- Built-in state, scheduling, WebSockets and MCP support
- SDK is open source; runs on Cloudflare's free tier to start
Vapi
Real-Time Voice Agents
- Orchestrates STT/LLM/TTS providers of choice into one low-latency voice-agent pipeline
- Usage-based per-minute pricing with free trial minutes included
- SOC 2/HIPAA/PCI compliance add-ons for regulated call-center deployments
Retell AI
Real-Time Voice Agents
- Free starting credit with no contract required
- Supports swapping GPT, Claude or Gemini as the reasoning layer per agent
- Batch calling campaigns plus live AI-to-human call transfer built in
Bland AI
Real-Time Voice Agents
- All-in-one per-minute pricing bundles LLM+STT+TTS with no separate token pass-through charges
- Free start with call credits plus an inbound number included
- Tiered platform fees (Build/Scale) unlock lower per-minute rates for high volume
LiveKit Agents
Real-Time Voice Agents
- Apache-2.0 open-source framework, fully self-hostable on your own servers
- Native WebRTC client support across web/mobile/telephony out of the box
- Native Model Context Protocol (MCP) support for tool-using voice agents
Pipecat
Real-Time Voice Agents
- BSD-2-Clause open-source Python framework for real-time voice/multimodal agents
- Supports distributed multi-agent systems with handoffs over a shared bus
- Maintained by Daily with an active plugin ecosystem for STT/LLM/TTS providers
Ultravox
Real-Time Voice Agents
- Speech-native processing skips the STT-to-text bottleneck, preserving tone/cadence/pitch
- Free tier: 5¢/min including TTS for up to 5 concurrent calls
- Open-weight models (fixie-ai) published on Hugging Face for research use
- Open-source framework for phone voice agents, from an India-based team
- Connects to telephony, STT, LLM and TTS providers of your choice
- Supports Indian languages
- Self-host free; hosted platform is pay-as-you-go
- Wraps any text LLM with Kyutai's streaming speech-to-text and text-to-speech for voice conversation
- Open-source code and weights that can be self-hosted
- Low-latency interruptible conversation
- Free demo available online
- Open-source framework for real-time conversational voice and multimodal agents
- Modular graph of extensions in Python, Go, C++ and Node
- Ships a playground and a VAD and turn-detection model
- Free to self-host under an open license
- Open-source ESP32 voice chatbot with wake word, Opus streaming and a display
- Free official server lets personal users try a Qwen real-time model after registering
- Device-side and cloud MCP for controlling IoT gadgets
- MIT licensed firmware supporting many ESP32 chips
Browser Use
Browser & Computer-Use Agents
- Open-source library to run browser agents locally for free
- Hosted agent API billed per token + browser-hour
- Managed browser infrastructure for scaling agents
Browserbase
Browser & Computer-Use Agents
- Free tier: 1 browser-hour/month, 3 concurrent browsers, 3 agent runs
- Creator of Stagehand, an AI-native browser automation framework
- Agent identity management for logging into restricted sites
Skyvern
Browser & Computer-Use Agents
- Vision+LLM based automation that survives UI/DOM changes (no brittle selectors)
- 22,700+ GitHub stars, self-hostable via Docker
- Used by 500+ enterprises for workflow automation on arbitrary sites
Steel.dev
Browser & Computer-Use Agents
- Open-source browser API for fleets of cloud browsers
- Free launch tier with one-time starting credits, no card required
- Built-in auto-CAPTCHA solving and proxy management, sessions up to 24h
Firecrawl
Browser & Computer-Use Agents
- Converts any site into clean LLM-ready markdown/structured data
- Free tier: 1,000 credits/month, no card required
- Crawl, scrape, map and search endpoints purpose-built for RAG/agent pipelines
Playwright MCP
Browser & Computer-Use Agents
- Official Microsoft MCP server exposing Playwright browser control to any MCP client
- Uses accessibility snapshots instead of screenshots/vision, faster and more deterministic
- 36k+ GitHub stars, Apache-2.0 licensed
Simular
Browser & Computer-Use Agents
- Sai: always-on computer-use agent operating a private cloud virtual desktop
- 72.6% success on computer-use benchmarks, above reported human baseline
- Works across desktop GUI, APIs, terminals, and code, not just browser tasks
- Open-source agent working across the browser and local files
- Fully open stack: MagenticBrain and Fara 1.5 models with open weights on Hugging Face
- Human-in-the-loop approvals before risky actions
- Free to run locally
- Parses UI screenshots into structured interactable elements
- Lets vision LLMs drive GUIs without DOM access
- Open-source with weights on Hugging Face
- Used by computer-use agent stacks
- Python SDK for building reliable browser-automation agents on Amazon Nova
- Free to start at nova.amazon.com/act with an API key
- Combines natural-language steps with Playwright code
- Open-source SDK
- Open-source multimodal agent stack that controls desktop and browser from screenshots
- Agent TARS CLI and desktop app with MCP support
- Runs with UI-TARS models or other vision LLMs
- Local operator mode keeps data on device
- JavaScript in-page GUI agent that controls web interfaces via natural language
- Embeds into your own web app with no browser extension
- Uses text DOM instead of screenshots
- Bring your own LLM API key
- Open-source SDK adding act, extract and observe AI primitives on top of Playwright
- Runs locally with your own model key
- Optional Browserbase cloud browsers (separate free tier)
- Chrome extension that runs a multi-agent team to automate browsing tasks
- Uses your own API keys or local models, so nothing extra is charged
- Everything runs locally in the browser and is open source
- Free alternative to paid browser operator agents
- Open-source Chromium browser with a built-in AI agent that automates web tasks
- Runs with local models via Ollama or your own keys, keeping data on your machine
- Positioned as a free alternative to Comet and ChatGPT Atlas
- Supports MCP servers
- Phone agent that reads the screen and taps through apps to finish natural-language tasks
- Supports Android, HarmonyOS and iOS via ADB, HDC or WebDriverAgent
- Asks for confirmation on sensitive actions and allows human takeover
- Apache 2.0; uses Zhipu/ModelScope API or a self-hosted model
Smithery
MCP Ecosystem
- Marketplace of 14,000+ hosted MCP servers with one-click connect
- Handles OAuth/credential plumbing automatically for MCP tool auth
- Connections reusable across Claude, GPT and other MCP clients
Composio
MCP Ecosystem
- Managed auth + tool-call infrastructure for agents across 250+ apps
- Free tier: 20,000 tool calls/month with community support
- Ships both MCP servers and native SDKs for major agent frameworks
Glama
MCP Ecosystem
- Indexes and security-scans thousands of MCP servers for compatibility/safety
- API gateway for connecting to MCP servers programmatically
- Free account tier plus paid gateway/enterprise options
Cloudflare MCP
MCP Ecosystem
- Build and deploy remote MCP servers directly on Cloudflare Workers with built-in OAuth
- Ships an Agents SDK for stateful, durable AI agents alongside MCP hosting
- Runs on Cloudflare's free-tier-eligible Workers platform, scaling to global edge
MCP Registry (Official)
MCP Ecosystem
- The canonical open-source specification and docs for the Model Context Protocol
- Reference server/client SDKs and the official server registry
- Backed across the ecosystem — Claude, ChatGPT, VS Code, Cursor, MCPJam all implement it
Zapier MCP
MCP Ecosystem
- Turns any of Zapier's 9,000+ app integrations into callable MCP tools for any AI client
- Pre-authenticated connections avoid per-app OAuth setup for agent builders
- Included on all Zapier plans (including free), billed against existing task quota
- Open protocol for agents from different vendors to discover and talk to each other
- SDKs in Python, JS, Java, .NET and Go
- Now hosted by the Linux Foundation
- Complements MCP for agent-to-agent communication
- Pythonic framework for building MCP servers and clients in a few lines
- Proxying, composition and auth helpers
- Open source, Apache-licensed
- Visual testing and debugging tool for MCP servers
- Call tools, browse resources and view logs interactively
- Runs locally via npx
- Reference MCP servers such as filesystem, git, fetch and memory
- Starting point for building your own servers
- Open source
- GitHub's official MCP server for repos, issues, PRs and Actions
- Works with Claude, Copilot, Cursor and other MCP clients
- Open source; needs a GitHub token
- Official Python SDK for MCP servers and clients
- Stdio, SSE and streamable HTTP transports
- Open source
- Official TypeScript SDK for MCP servers and clients
- Streamable HTTP, stdio and auth helpers
- Open source
- Fullstack framework for building MCP servers and MCP Apps for ChatGPT and Claude
- Client library to connect any LLM to MCP servers
- Open source
- Aggregates many MCP servers behind one endpoint with a web UI
- Namespaces, middleware and per-tool filtering
- Docker-based, self-hosted
- Free and open source
Mem0
Agent Memory & RAG-as-a-Service
- Free Hobby tier: unlimited end users, 10K add / 1K retrieval requests/month
- Graph memory and entity linking for agent context
- Open-source core plus managed cloud API
Zep
Agent Memory & RAG-as-a-Service
- Free plan: 10,000 monthly credits, 2 projects, 200ms retrieval
- Graph RAG with automated context assembly from chat + business data
- Temporal knowledge graph for tracking how facts change over time
Supermemory
Agent Memory & RAG-as-a-Service
- Free monthly usage allowance plus a Supermemory MCP server
- Native connectors for Google Drive, Notion, OneDrive as memory sources
- Deduplication so repeated content isn't rebilled
Letta
Agent Memory & RAG-as-a-Service
- Free BYOK plan supporting up to 3 stateful agents
- Stateful-agent runtime with persistent memory, desktop app, CLI and API
- Open-source framework (formerly MemGPT) plus a managed cloud
- Open-source RAG engine with deep document parsing and agent workflows
- Grounded citations and template-based chunking
- Self-host with Docker; bring your own LLM
- Simple, fast graph-based RAG from HKU Data Science lab (EMNLP 2025)
- Combines knowledge-graph and vector retrieval
- Works with local or hosted LLMs
- Open-source memory platform that turns data into a knowledge graph plus vectors for agents
- Python API with pluggable graph, vector and relational stores
- Self-host free; cloud option exists
- Framework for building real-time temporal knowledge graphs for AI agents
- Powers Zep's memory layer; runs standalone
- Open source, works with Neo4j and other graph DBs
- Memory operating system for LLM agents with hybrid retrieval and persistent memory
- Open source and self-hostable, with a cloud option
- Built for multi-agent and personal assistants
- Backed by MemTensor, a Shanghai team
- Packs agent memory into a single portable file with no server or database
- Offline retrieval with no cloud dependency
- Open source with SDKs
- Aimed at replacing complex RAG pipelines
- MCP server that stores AI conversation memory as local Markdown notes
- Works with Claude Desktop and other MCP clients, and is readable in Obsidian
- Everything stays on your disk
- Open source core is free; optional paid cloud sync
- LLM-agnostic memory layer that captures agent context as structured state
- Works with LangChain, Pydantic AI, Agno and MCP clients such as Claude Code
- Open source under Apache 2.0, with free self-host
- Hosted cloud with an always-free development tier
AI Agents & Automation — straight answers
What ai agents & automation tools does Flocci list?
Flocci AI Tools lists 126 ai agents & automation tools, ordered free tiers first: AutoGPT, Bolna, Flowise, Google Opal and Kortix (Suna). 123 of the 126 are free or have a free tier. Every entry states what it uniquely does, not a score.
Which ai agents & automation tools are completely free?
Yes — 76 of these are marked fully free with no paid plan attached: AutoGPT, Bolna, Flowise, Google Opal and Kortix (Suna). The rest are freemium, trial or paid, and each row states which.
How is AI Agents & Automation organised?
Into 7 sub-categories — General Autonomous Agents, Workflow Automation, Agent Frameworks (Developers), Real-Time Voice Agents, Browser & Computer-Use Agents, MCP Ecosystem, Agent Memory & RAG-as-a-Service — holding 126 tools between them. Each sub-category has its own page with the same pricing labels and capability lists.