Hivemind
Hivemind adds a shared memory and skill layer for coding agents, aiming to preserve useful traces, codify repeatable patterns, and make one engineer's agent work reusable across the whole team.
agent memoryshared knowledgecoding agents
1390
AI Agent
51 tools in this category
DecisionBox
DecisionBox is an autonomous warehouse-analysis agent that writes and validates its own SQL, then turns findings into a ranked backlog of insights instead of waiting for a human to ask the right question.
AI data analystwarehouse discoveryautonomous SQL
1080
Agent Browser Shield
Agent Browser Shield is an alpha Chromium MV3 extension with 35+ local page-cleaning, PII-masking, dark-pattern, and prompt-injection rules for browser agents. This review examines its benchmark, privacy, PolyForm Shield license, false-positive risk, deployment, testing, and layered-security role.
browser agent securityprompt injection defensePII masking
1470
Asteroid
Asteroid is a healthcare-focused browser and computer-use platform for connecting EHRs, payer portals, registries, desktop apps, and Citrix workflows that lack clean APIs. This review covers architecture, HIPAA-sensitive controls, pilot design, pricing evidence, and alternatives.
browser AI agentsportal automationAI workflow builder
910
Kimi WebBridge
Kimi WebBridge is a local browser bridge for AI agents. It pairs a browser extension with a local service so an agent can click, navigate, fill forms, screenshot, and keep working across sites that do not expose clean APIs.
browser agent bridgeChrome DevTools Protocollocal browser automation
1320
Hermes WebUI
Hermes WebUI is a self-hosted browser interface for Hermes Agent that brings chat, files, sessions, memory, and agent controls into a web app without giving up the underlying CLI-style power.
AI agentself-hostedweb UI
950
Envelope
Envelope is a platform and open standard for defining AI agent teams, versioning how they work, and deploying them across orchestration environments without forcing teams into one proprietary workflow.
agent teamsworkflow automationno-code AI
910
Band
Band is an infrastructure layer for multi-agent systems, giving agents persistent identity, structured memory, coordination, and auditability across frameworks.
multi-agentagent coordinationstructured memory
1450
Agentspan
Agentspan is an MIT-licensed, self-hostable runtime that compiles AI agents into durable Conductor workflows. This practical guide explains crash recovery, approvals, retries, observability, framework integrations, security boundaries, rollout tests, costs, and alternatives.
durable executionagent runtimeworkflow reliability
1540
Hindsight
Hindsight is an open-source agent memory system that gives AI agents durable, structured memory so they can recall facts, learn from outcomes, and improve across sessions.
agent memorypersistent memorylong-term context
1310
OpenSwarm
OpenSwarm is an open-source multi-agent workspace that turns one prompt into coordinated outputs across research, docs, slides, data, images, and other deliverables.
multi-agentparallel workflowsresearch automation
940
OpenAgent
OpenAgent is a self-hosted personal AI assistant platform that combines MCP, RAG, browser and computer use, and multi-provider model support in one package.
self-hostedmcpknowledge base
1640
Open Comet
Open Comet is an open-source browser sidepanel agent for researching pages, taking actions, and running multi-step web workflows with local or BYOK models.
browser agentdeep researchbrowser automation
1110
Jarvis Registry
Jarvis Registry is an enterprise MCP and agent gateway for connecting copilots to internal tools through one governed layer with identity, ACLs, discovery, and observability.
MCP gatewayenterprise agentsaccess control
920
AINL
AINL is an AI-native language and runtime model for graph-based agent workflows, constraints, and tool-driven execution with less dependence on long prompt loops.
agent workflowsgraph runtimeconstraints
1020
mem9
mem9 gives coding agents and workflow apps one shared persistent memory layer so context survives across sessions, machines, and different agent runtimes.
agent memoryshared contextMCP
1060
iii
iii is a code-first runtime for building APIs, workflows, observability, and AI agents on one shared execution surface instead of stitching every backend component together by hand.
agent runtimebackend frameworkworkflows
930
Memory Store
Memory Store syncs conversations, snippets, and decisions from the tools your team already uses, then exposes that context as shared memory for agents and humans through MCP.
shared memoryMCPteam knowledge
970
Owlish
Owlish turns websites, FAQs, docs, and PDFs into customer-support agents that can answer, act, cite sources, and hand work off to humans.
AI support agentcustomer supportdocs chatbot
890
TradingAgents
TradingAgents is an open-source multi-agent trading framework that coordinates analyst, researcher, trader, and risk roles to study markets with LLM-driven workflows.
multi-agent tradingopen sourcefinancial research
990
OpenHuman
OpenHuman is a personal AI agent platform focused on private, powerful assistance for users who want more control than consumer chatbot apps usually provide.
personal AIAI agentprivate AI
1030
Flowly
Flowly is a native desktop AI assistant for macOS, Windows, and Linux that can act across apps and browser tabs with chat, voice, and mobile companion workflows.
Flowlydesktop AI assistantAI agent
1090
Poke
Poke is a proactive personal AI assistant available through Apple Messages, Telegram, WhatsApp and RCS. This independent guide examines its recipes, account connections, privacy terms, confirmation boundaries, reliability, task selection, alternatives and a safe two-week trial.
Pokepersonal AI assistantAI agent
1380
Perplexity Computer
Perplexity Computer is a 2026 multi-model agent system for long-running research, coding, finance, and workflow execution across cloud and Mac-based environments.
Perplexity ComputerPersonal Computermulti-model agent
950