agentmode.aiAsk for help
Open sectionsClose sections

Ecosystem overview

Who makes what in the agent field?

Search for a system, then follow it to the organizations, standards, and ideas around it.

Explore the full map

An index you can move through

How does the agent field fit together?

Search for a term, system, organization, or standard. The map keeps connected records nearby. Each line is a path to follow, not a verdict. Open a record to read the source behind it. Use the map to choose the next page, not to settle the question by itself.

Same deskUsesGoverned
Browse the visible records 177 records
  1. CursorSystemsCursor is a code editor built from Visual Studio Code, with an agent that can plan and make coordinated changes across several files.Source
  2. Google AntigravitySystemsGoogle Antigravity is a learning-focused development environment in Google's IDX family with access to supported coding models.Source
  3. Gemini CLISystemsGemini CLI is Google's open-source terminal agent for reading code, making changes, using tools, and working with Gemini models.Source
  4. Kilo CodeSystemsKilo Code is a coding agent with structured working modes and controls for how much project context it reads.Source
  5. Copilot WorkspaceSystemsCopilot Workspace is a GitHub project that helps turn an issue into a plan, code changes, and a pull request.Source
  6. QodoSystemsQodo reviews code changes with repository context and checks whether a pull request meets its stated purpose.Source
  7. LovableSystemsLovable turns a conversation about an application into software that a user can edit and deploy.Source
  8. DyadSystemsDyad is an open-source, local-first application builder that turns plain-language requests into software without requiring code.Source
  9. LangGraphSystemsLangGraph is a low-level orchestration framework for agents that need durable state, human review, and long-running execution.Source
  10. HaystackSystemsHaystack is an open-source orchestration framework for production AI applications that use retrieval, routing, memory, agents, or multimodal data.Source
  11. MastraSystemsMastra is a TypeScript framework for AI applications and agents, with tools for workflows, memory, retrieval, evaluation, and deployment.Source
  12. Google ADKSystemsGoogle's Agent Development Kit is a code-first Python toolkit for building, evaluating, and deploying AI agents.Source
  13. CrewAISystemsCrewAI organizes autonomous agents into role-based crews and gives them tasks they can complete together.Source
  14. OpenAI Agents SDKSystemsThe OpenAI Agents SDK is a lightweight framework for tool-using agents, handoffs, guardrails, sessions, and traces.Source
  15. Strands AgentsSystemsStrands Agents supplies an open-source SDK for building and controlling production agent harnesses across models and clouds.Source
  16. AgentScopeSystemsAgentScope is an open-source framework for building and running agents whose actions can be inspected and understood.Source
  17. SmolagentsSystemsSmolagents is Hugging Face's small agent library for systems that plan and act by writing code or calling tools.Source
  18. OpenClaw Agent TemplatesSystemsOpenClaw Agent Templates is a library of ready-made role and behavior files for setting up OpenClaw agents for common jobs.Source
  19. Claude in ChromeSystemsClaude in Chrome is Anthropic's browser agent for working with pages inside Google's Chrome browser.Source
  20. FellouSystemsFellou is an agentic browser with editable visual workflows and memory for work that spans more than one step.Source
  21. Agent S2 (Simular)SystemsAgent S2 is Simular's open-source framework for agents that operate graphical user interfaces.Source
  22. Amazon Nova ActSystemsAmazon Nova Act is an AWS system for building agents that carry out browser tasks with enterprise controls.Source
  23. ElevenLabsSystemsElevenLabs provides speech models and tools for building voice agents, producing audio, and handling spoken conversations.Source
  24. SynthflowSystemsSynthflow is a no-code platform for small businesses to build voice agents from templates.Source
  25. RasaSystemsRasa is an open-source platform for training and self-hosting conversational assistants with natural-language understanding.Source
  26. n8nSystemsn8n is a workflow-automation platform that connects applications and can place AI agents inside visual or coded workflows.Source
  27. TemporalSystemsTemporal provides durable execution for agent workflows that must survive failures, waits, and long-running jobs.Source
  28. LangflowSystemsLangflow is an open-source visual builder for multi-agent systems and retrieval-augmented generation pipelines.Source
  29. FastAgencySystemsFastAgency is an open-source framework for exposing multi-agent workflows through web application programming interfaces.Source
  30. AdaSystemsAda is a customer-service platform for agents that answer and resolve requests across digital and voice channels, using approved playbooks when a job needs fixed steps.Source
  31. Salesforce Einstein + AgentforceSystemsSalesforce combines Einstein predictions with Agentforce agents inside its customer-data and automation platform.Source
  32. Dynamics 365 CopilotSystemsDynamics 365 Copilot helps people draft, summarize, and translate work inside Microsoft's business applications and Power Platform.Source
  33. ClaySystemsClay combines company data, enrichment services, and AI to prepare personalized sales research and outreach.Source
  34. LavenderSystemsLavender is an email coach that scores sales messages and suggests changes while a person writes.Source
  35. Perplexity ProSystemsPerplexity Pro is a paid AI search service that investigates questions and links its answers to current web sources.Source
  36. Hex AISystemsHex AI adds analysis assistants to a collaborative workspace for data, notebooks, reports, and applications.Source
  37. RAGFlowSystemsRAGFlow is an open-source retrieval engine for building grounded question-answering applications and agent workflows.Source
  38. iGPTSystemsiGPT turns email threads into structured data that an agent can search, compare, and reason over.Source
  39. OpenClawSystemsOpenClaw is a self-hosted agent that can work through messaging applications and use community-built skills to carry out tasks.Source
  40. LibreChatSystemsLibreChat is a self-hosted chat interface that connects to several model providers and supports extensions.Source
  41. DB-GPTSystemsDB-GPT is an open-source framework for asking questions of private data with locally run language models.Source
  42. Cursor AI Automated TeamSystemsCursor AI Automated Team is a four-role software workflow that passes written tasks among planning, development, operations, and testing agents.Source
  43. MCP (Model Context Protocol)StandardsModel Context Protocol is an open standard that gives AI applications one consistent way to connect models with tools and data.Source
  44. A2A (Agent-to-Agent)StandardsA2A is an open protocol that lets one AI agent find another, send it work, follow its progress, and receive the result.Source
  45. MCP AppsStandardsMCP Apps lets a tool return an interactive form, chart, or dashboard that appears inside an agent conversation.Source
  46. HCS (Hashgraph Consensus Service)StandardsHashgraph Consensus Service gives agents shared rules for identity, messages, and ordering records on Hedera's public network.Source
  47. LangSmithBenchmarksLangSmith is LangChain's platform for tracing agent runs, testing behavior, and comparing evaluations.Source
  48. HeliconeBenchmarksHelicone is an open-source observability platform for logging, tracing, and evaluating calls to language models.Source
  49. Terminal-BenchBenchmarksTerminal-Bench measures how well agents complete practical tasks inside a command-line environment.Source
  50. Guardrails AISystemsGuardrails AI adds structural, type, and quality checks to outputs produced by language-model applications.Source
  51. OWASP Top 10 for Agentic AppsSystemsThe OWASP Top 10 for Agentic Applications lists common security risks in agents and practical ways to reduce them.Source
  52. Credo AI Agent GovernanceSystemsCredo AI Agent Governance helps organizations list AI systems, apply policy rules, and record the evidence needed for review.Source
  53. AuditOne TIC OS Stage-1 Audit AgentSystemsAuditOne's Stage-1 Audit Agent prepares risk assessments and supporting documents for technology audits.Source
  54. Microsoft Security CopilotSystemsMicrosoft Security Copilot helps security teams investigate threats, respond to incidents, and work across Microsoft security products.Source
  55. Anthropic Claude CodeSystemsClaude Code is Anthropic's coding agent for reading codebases, editing files, running commands, and helping developers complete software work.Source
  56. Manus AISystemsManus is a general AI agent that carries out multi-step computer work and returns finished outputs rather than only a chat response.Source
  57. OpenAI CodexSystemsCodex is OpenAI's coding agent for working on software tasks in local tools, cloud environments, and collaborative development workflows.Source
  58. ByteDance Agent TARSSystemsAgent TARS is ByteDance's open-source multimodal stack for agents that operate browsers and computers through a command-line interface.Source
  59. Glean AgentsSystemsGlean Agents lets companies create workplace agents that search company knowledge, use business tools, and carry out repeatable jobs.Source
  60. Microsoft Copilot StudioSystemsMicrosoft Copilot Studio is a managed platform for creating, connecting, and governing agents inside Microsoft and business systems.Source
  61. WRITER Action AgentSystemsWRITER Action Agent carries out business tasks across approved tools while keeping its work inside Writer's enterprise AI platform.Source
  62. AI agentConceptsA system that observes a setting, chooses goal-led actions, and acts on that setting.Source
  63. agentic AIConceptsAI designed to choose and carry out actions toward a goal, often through one or more agents.Source
  64. environmental interactionConceptsThe exchange in which an agent observes a world, acts on it, and receives new information in return.Source
  65. observationConceptsInformation an agent gets from its setting before or after it acts.Source
  66. plannerConceptsThe part of an agent system that proposes goals, steps, dependencies, or action sequences.Source
  67. LLM-profiled roleConceptsAn agent role shaped mainly by instructions about its skills, duties, and limits.Source
  68. planning workflowConceptsA workflow in which the system creates, checks, and carries out a plan.Source
  69. tool useConceptsThe use of an outside tool for its result or for the change it causes.Source
  70. tool callingConceptsThe process by which a model or agent requests that software run a named tool with stated arguments.Source
  71. tool registryConceptsA directory that lists tools and the information needed to discover and call them.Source
  72. tool resultConceptsThe data or error returned after a tool invocation.Source
  73. autonomous tool useConceptsTool use in which the agent chooses when, why, and how to call a tool without approval for each call.Source
  74. direct planningConceptsA model writes a plan without first searching through many other paths.Source
  75. search treeConceptsA branching map of choices and the states that may follow them.Source
  76. simulation-based planningConceptsTesting actions in a model or mock world before using them in the real one.Source
  77. chain of thoughtConceptsText or tokens a model produces as steps before an answer. They may not show its true internal reasoning.Source
  78. feedback learningConceptsA way to improve later choices by using signals from past results.Source
  79. embodied environmentConceptsA real or simulated world where an agent acts through a body, robot, or set of sensors.Source
  80. agent swarmConceptsA group of agents that often coordinate through local rules or shared signals.Source
  81. worker agentConceptsAn agent that does tasks assigned by a lead agent or system.Source
  82. handoffConceptsPassing control, context, or duty from one agent to another.Source
  83. orchestrationConceptsThe logic that decides which agent, tool, or workflow runs, in what order, with what state, and when it stops.Source
  84. blackboard architectureConceptsA design in which several agents or modules read from and write to one shared working state.Source
  85. context cachingConceptsSaving reused prompt or context material so later model calls can be faster or cheaper.Source
  86. short-term memoryConceptsState kept for the current run or conversation, such as messages, tool results, plans, and checkpoints.Source
  87. procedural memoryConceptsStored knowledge of how to perform a task, such as rules, routines, or reusable skills.Source
  88. memory poisoningConceptsAn attack that plants false or harmful facts in memory to sway later actions.Source
  89. durable executionConceptsWork that can survive a restart, wait for an event, and resume from saved state.Source
  90. long-running agentConceptsAn agent designed to continue across long waits, many steps, or more than one user session.Source
  91. approval gateConceptsA point where an agent must stop and get consent before it takes a high-risk step.Source
  92. guardrailConceptsA rule or check that blocks, changes, or escalates an input, output, or action when a condition is met.Source
  93. least privilegeConceptsThe rule that a user, agent, or service should receive only the access needed for its current task.Source
  94. tool poisoningConceptsAn attack that alters a tool, its description, or its output so an agent is misled or compromised.Source
  95. agent identityConceptsThe names, traits, and proof that let a system tell one agent from another.Source
  96. trajectoryConceptsThe ordered record of an agent’s states, actions, inputs, and outputs during a run.Source
  97. task successConceptsA defined measure of whether an agent achieved the intended outcome.Source
  98. red teamingConceptsThe deliberate search for ways a system can fail, be misused, or be attacked.Source
  99. error recoveryConceptsFinding a failure, returning to a safe state, and choosing the next useful step.Source
  100. freshness windowConceptsThe maximum age evidence may reach before it must be checked again.Source
  101. attestationConceptsA signed or recorded statement that a required action, check, or condition was completed.Source
  102. skill registryConceptsA list of reusable skills, what they do, how to call them, and what they need.Source
  103. agent cardConceptsA file that tells other systems who an agent is, what it can do, and how to reach it.Source
  104. agentic commerceConceptsTrade in which agents help find, buy, sell, or pay for goods under set rules.Source
  105. AnthropicOrganizationsAnthropic develops the Claude model family and tools for building AI assistants and agents with an emphasis on safety research.Source
  106. MetaOrganizationsMeta develops the Llama model family, AI assistants, and research used in open and commercial agent projects.Source
  107. ServiceNowOrganizationsServiceNow develops AI agents for completing work across service, employee, customer, and technology-management workflows.Source
  108. LlamaIndexOrganizationsLlamaIndex develops tools for document agents that need to parse, retrieve, and reason over private information.Source
  109. CognitionOrganizationsCognition builds Devin, a software-engineering agent designed to plan and complete coding work with developer oversight.Source
  110. WriterOrganizationsWriter develops an enterprise AI platform for creating agents, applications, and governed workflows on company data.Source
  111. Automation AnywhereOrganizationsAutomation Anywhere combines business-process automation with AI agents that carry work across company applications.Source
  112. AdaOrganizationsAda builds customer-service agents that answer questions and resolve requests across digital and voice channels.Source
  113. Arize AIOrganizationsArize AI makes observability and evaluation software for teams that need to inspect model, retrieval, and agent behavior.Source
  114. Patronus AIOrganizationsPatronus AI makes evaluation and security tools for finding failures in language models and agent systems before deployment.Source
  115. Robust IntelligenceOrganizationsRobust Intelligence developed testing and protection software for AI models; Cisco acquired the company, so current offerings should be checked there.Source
  116. E2BSystemsE2B provides temporary, isolated Linux computers in which agents can run code, process data, use tools, or control a virtual desktop.Source
  117. BeeAI FrameworkSystemsBeeAI Framework is an open-source Python and TypeScript toolkit for building production systems in which several agents work together.Source
  118. AgentOpsSystemsAgentOps helps teams trace, test, debug, and monitor AI agents while they are being built and run.Source
  119. MoltiverseConceptsA name used by the community around OpenClaw.Source
  120. Agent Payments ProtocolStandardsAgent Payments Protocol is an open set of rules for payments that an agent starts only after a user gives clear authority.Source
  121. Agentic AI FoundationOrganizationsThe Agentic AI Foundation is a Linux Foundation project that houses open infrastructure for agents, including Model Context Protocol, goose, and AGENTS.md.Source
  122. NIST AI Agent Standards InitiativeStandardsThe NIST AI Agent Standards Initiative develops guidance for agents that must work together, prove identity, use authority safely, and resist attacks.Source
  123. Agent Identity ProtocolStandardsAgent Identity Protocol is a draft set of rules for proving an AI agent's identity, permissions, delegation, and accountability.Source
  124. OpenAI released a major Codex update adding computer operation, broader app and tool access, image generation, memory, repeatable work, SSH, and an in-app browser.SignalsOpenAI released a major Codex update adding computer operation, broader app and tool access, image generation, memory, repeatable work, SSH, and an in-app browser.Source
  125. Google launched Managed Agents in the Gemini API, allowing developers to run Antigravity or custom agents in isolated cloud sandboxes and define them with AGENTS.md and SKILL.md files.SignalsGoogle launched Managed Agents in the Gemini API, allowing developers to run Antigravity or custom agents in isolated cloud sandboxes and define them with AGENTS.md and SKILL.md files.Source
  126. Anthropic launched Claude Science in beta as a multi-agent scientific workbench with more than 60 curated skills and connectors plus a reviewer agent.SignalsAnthropic launched Claude Science in beta as a multi-agent scientific workbench with more than 60 curated skills and connectors plus a reviewer agent.Source
  127. AWS announced limited-preview access on Amazon Bedrock to OpenAI models, Codex, and Managed Agents.SignalsAWS announced limited-preview access on Amazon Bedrock to OpenAI models, Codex, and Managed Agents.Source
  128. AWS made its managed remote MCP server generally available, exposing authenticated access to AWS services through a fixed tool surface.SignalsAWS made its managed remote MCP server generally available, exposing authenticated access to AWS services through a fixed tool surface.Source
  129. Power Systems Agent BenchmarkBenchmarksThe paper introduced an executable benchmark with 41 task families across eight power-engineering areas and deterministic evaluators.Source
  130. Behavioral state decaySignalsIn long-horizon tasks, decision-relevant state is often scattered across an expanding trajectory, while the action agent must surface it and act.Source
  131. Market-stability mechanisms for LLM-agent societiesSignalsSelf-interested agents, left unconstrained, tend toward defection in repeated social dilemmas, causing cooperative gains from trade to collapse.Source
  132. G-FrameSystemsG-Frame is an adaptive multi-agent framework integrating Bayesian and team game principles, establishes an automated closed-loop for high-quality data synthesis and model training.Source
  133. Multi-Agent Privacy FirewallSystemsThe Multi-Agent Privacy Firewall is an open-source guard between a user and language-model services that checks both browser and software requests for privacy risk.Source
  134. PrismataSystemsPrismata is a defense enforcing contextual least privilege for web agents, constraining both what the agent sees and what it can do.Source
  135. Harness engineeringSignalsHarness Engineering moves repeatable agent behavior into code, schemas, checks, and records around a model so the system can be inspected and changed safely.Source
  136. AI-agent code-review causal modelSignalsThe AI Agent Code Review Causal Model maps how team expertise and review practices shape the effect of agent-written pull requests on software work.Source
  137. Jailbreak storage-reader regenerationSystemsJailbreak is a research method for recovering database content directly from storage files when the normal database engine is unavailable.Source
  138. Action-graded severity scaleBenchmarksThe Action-Graded Severity Scale ranks an agent's harmful actions from reversible mistakes to actions that cross boundaries or gain more power.Source
  139. Deterministic policy gates for tool-using agentsSignalsDeterministic Policy Gates inspect an agent's proposed tool call and current state before allowing the agent to change anything.Source
  140. Iterative tool optimization for self-evolving agentsSignalsEvoSOP lets an agent turn repeated sequences of small tool actions into reusable procedures, then merge, test, improve, or remove those procedures.Source
  141. Progressive crystallizationSignalsProgressive crystallization is a lifecycle that treats agent exploration as a discovery mechanism rather than a permanent execution model.Source
  142. Autogenic network managementSignalsAutogenic network management is a reference architecture that extends agentic capabilities with self-programming, self reflection, self-orienting, and self-architecting capabilities.Source
  143. Recall-controlled early-abort probe cascadeSignalsThe Recall-Controlled Early-Abort Probe Cascade watches an agent's internal state and stops runs that are unlikely to succeed before they waste more computing time.Source
  144. RuBenchBenchmarksRuBench is a benchmark of repository-maintenance tasks written as native Russian customer requests and graded with withheld regression tests.Source
  145. TOFFEESystemsTOFFEE is a system for synthesizing high-quality data agent trajectories from given data environments via Monte Carlo Tree Search (MCTS) with adaptive model selection and cross-task prefix reuse.Source
  146. Deliberative-collaboration agent benchmarkBenchmarksThe Deliberative Collaboration Agent Benchmark tests whether several agents can share different pieces of information and reason together toward one decision.Source
  147. Prompt CoachSystemsPrompt Coach is an agentic tutor that helps developers learn how to craft high-quality code-generation prompts through Socratic guidance embedded in-flow within their IDE.Source
  148. MCP-enabled IPoDWDM lifecycle automationSignalsMCP-Enabled IPoDWDM Lifecycle Automation uses agents and Model Context Protocol tools to configure, monitor, and adjust optical networks from end to end.Source
  149. NapMemSystemsNapMem is a framework for learning to use long-term user memory as a structured action space rather than passively retrieved context.Source
  150. Unicode TAG-Block MCP ConcealmentSignalsUnicode TAG-Block MCP Concealment is an attack that hides tool instructions from a human approval screen while leaving the same bytes visible to the agent model.Source
  151. Agent Mutation TaxonomySignalsEach agent's deployed system commits to a distinctive mutation vocabulary, and each performance strategy activates a largely disjoint category subset.Source
  152. aiAuthZSystemsaiAuthZ is an authorization gateway that moves the safety decision off the agent's host.Source
  153. GaPSystemsGraph-as-Policy is a multi-agent robotics harness that assembles perception, planning, and control skills into a task graph, then rehearses alternatives in simulation.Source
  154. MetaSkill-EvolveSystemsMetaSkill-Evolve is a research framework in which an agent improves both the skill used for a task and the method used to improve that skill.Source
  155. PDEFlowSystemsPDEFlow is an autonomous agentic framework that turns user-level ODE and PDE descriptions into solver-backed neural-operator pipelines.Source
  156. STAPOSignalsSelective Trajectory-Aware Policy Optimization is a training method that finds doubtful steps in a long agent run and focuses learning on those steps without destabilizing the rest.Source
  157. Multi-Turn On-Policy Distillation with Prefix ReplaySignalsReplayed-Prefix On-Policy Distillation trains an agent by letting it continue selected parts of saved expert examples while receiving guidance at each step.Source
  158. RSPOSignalsReward-Swap Policy Optimization is a training method that uses detailed step-by-step rewards to improve learning from final outcomes.Source
  159. MRMSSystemsMRMS is a memory system that combines structured records, similarity search, graph links, and time rules so a long-lived agent can revise what it remembers.Source
  160. HCRCSystemsHCRC is a verification framework that lets an agent move to the next step only after independent checks confirm the current step.Source
  161. Offline RL Harness ControlSignalsOffline RL Harness Control trains a small controller to improve how a fixed model checks, sequences, and manages agent work without retraining the model.Source
  162. UI-MOPDSignalsUI-MOPD is the first method that incorporates multi-teacher on-policy distillation into continual learning for GUI agents.Source
  163. HAS-BenchBenchmarksHAS-Bench tests how well people and AI agents work together when their roles, permissions, communication paths, and decision power vary.Source
  164. Agentic OperadSignalsAgentic Operad is a mathematical model for comparing the wiring of gene-regulation networks with the wiring of agent software.Source
  165. I-Don't-Know Function-Call FilterSignalsThe I-Don't-Know Function-Call Filter measures a model's uncertainty and blocks doubtful tool requests before an agent can carry them out.Source
  166. DualViewSystemsDualView tracks untrusted information across an agent's context, files, shell, network, and other agents by keeping a safe and an unrestricted view.Source
  167. Scaffolding Evolution EffectSignalsCoding agents, autonomous systems that use large language models (LLMs) to resolve software engineering tasks, rely on agentic scaffolding: a middleware layer in between a developer and a large language model that orchestrates system prompts, tool execution, context management, and iterative reasoning loops.Source
  168. Microsoft Teams FacilitatorSystemsA Teams meeting agent that can keep an agenda, create notes, answer questions, and track follow-up work.Source
  169. BenchLMBenchmarksAn owner-published AI model leaderboard with methodology, evidence-status lanes, and an agentic evaluation category.Source
  170. artificial intelligence (AI)ConceptsA machine system that predicts or makes choices for goals set by people.Source
  171. Visual Inspection of Policies (VIP)SystemsVisual Inspection of Policies uses recorded videos of an agent's behavior to choose which training tasks the agent should try next.Source
  172. CARLA-GSSystemsCARLA-GS is a modular corner-case synthesis pipeline that decouples visual representation, semantic reasoning, and physics-based execution while maintaining tight cross-module coupling.Source
  173. deployment simulation for LLM safetyBenchmarksDeployment Simulation for LLM Safety replays real conversation openings with a new model to estimate harmful behavior before that model reaches users.Source
  174. FRAMeSystemsFRAMe is an End-to-End Large Language Model (LLM) Flight Planning tool with RAG-based Memory and Multi-modal Coach Agent.Source
  175. Nimblemind Multi-Agent System (nMAS)SystemsNimblemind Multi-Agent System (nMAS) is a field-name-driven, evidence-linked extraction workflow, using 54 de-identified gastric biopsy pathology reports from a large healthcare system in Singapore.Source
  176. LLM agent failure taxonomySignalsThe LLM Agent Failure Taxonomy groups recurring agent failures in tool use, planning, long tasks, teamwork, safety, and benchmark design.Source
  177. CareConnectSystemsCareConnect is a safety-first conversational agent for healthcare logistics automation that leverages large language model (LLM) function calling, retrieval-augmented generation (RAG), and layered deterministic safety guardrails.Source

Organizations · 47 sourced records

Who is building in the agent field?

The AI agent ecosystem includes the labs, companies, foundations, and open projects building agent systems. This directory gives each organization one sourced record, a plain description, and a link to the page we checked. Use it to see who is active, then read the source before drawing a conclusion.

47 shown
001 · foundationsSource found

What is Ada?

Ada builds customer-service agents that answer questions and resolve requests across digital and voice channels.

002 · foundationsSource found

What is Agentic AI Foundation?

The Agentic AI Foundation is a Linux Foundation project that houses open infrastructure for agents, including Model Context Protocol, goose, and AGENTS.md.

003 · operationsSource found

What is Agentic.ai?

Agentic.ai is an agent-tool directory and studio that categorizes tools and evaluates their autonomy against a published scoring rubric.

004 · foundationsSource found

What is Amazon Web Services?

Amazon Web Services provides cloud infrastructure and managed tools for building, deploying, securing, and monitoring AI agents.

005 · foundationsSource found

What is Anthropic?

Anthropic develops the Claude model family and tools for building AI assistants and agents with an emphasis on safety research.

006 · foundationsSource found

What is Arize AI?

Arize AI makes observability and evaluation software for teams that need to inspect model, retrieval, and agent behavior.

007 · foundationsSource found

What is Automation Anywhere?

Automation Anywhere combines business-process automation with AI agents that carry work across company applications.

008 · foundationsSource found

What is Braintrust?

Braintrust supplies evaluation, tracing, prompt, and data tools for teams improving AI products and agents.

009 · foundationsSource found

What is Browserbase?

Browserbase provides hosted browser infrastructure for agents that must navigate websites reliably and at scale.

010 · foundationsSource found

What is Cognition?

Cognition builds Devin, a software-engineering agent designed to plan and complete coding work with developer oversight.

011 · foundationsSource found

What is CrewAI?

CrewAI develops software for designing, running, and monitoring teams of role-based AI agents.

012 · foundationsSource found

What is ElevenLabs?

ElevenLabs develops voice models and a conversational-agent platform for spoken customer and product experiences.

013 · foundationsSource found

What is Galileo?

Galileo makes evaluation and observability tools for measuring the quality, safety, and reliability of generative AI systems.

014 · foundationsSource found

What is Glean?

Glean builds enterprise search and agent products that work with a company's people, knowledge, and applications.

015 · foundationsSource found

What is Google DeepMind?

Google DeepMind is Google's AI research lab, responsible for model research and systems that include the Gemini family.

016 · foundationsSource found

What is HiddenLayer?

HiddenLayer provides security products for detecting attacks and weaknesses in machine-learning models and AI applications.

017 · foundationsSource found

What is Hugging Face?

Hugging Face runs an open platform for sharing models, datasets, applications, and agent-development libraries.

018 · foundationsSource found

What is Humanloop?

Humanloop created evaluation and prompt-management software for teams testing language-model applications; check its current ownership and availability before buying.

019 · foundationsSource found

What is IBM?

IBM develops watsonx products for building, governing, and operating AI across enterprise data and workflows.

020 · foundationsSource found

What is Intercom?

Intercom builds customer-service software around Fin, an AI agent that answers and resolves support requests.

021 · foundationsSource found

What is Invariant Labs?

Invariant Labs researches and builds security controls for AI agents, including defenses against unsafe tool use and prompt attacks.

022 · foundationsSource found

What is Lakera?

Lakera develops security software for protecting generative AI applications from prompt attacks, unsafe output, and data leakage.

023 · foundationsSource found

What is LangChain?

LangChain develops open-source agent frameworks and LangSmith, a platform for tracing, evaluating, and deploying agent systems.

024 · foundationsSource found

What is Langfuse?

Langfuse provides open-source tracing, evaluation, prompt, and metrics tools for language-model applications.

025 · foundationsSource found

What is LiveKit?

LiveKit provides real-time voice, video, and transport infrastructure for conversational and multimodal agents.

026 · foundationsSource found

What is LlamaIndex?

LlamaIndex develops tools for document agents that need to parse, retrieve, and reason over private information.

027 · foundationsSource found

What is Meta?

Meta develops the Llama model family, AI assistants, and research used in open and commercial agent projects.

028 · foundationsSource found

What is Microsoft?

Microsoft builds Copilot products, agent-development platforms, cloud services, and research tools for business and software work.

029 · foundationsSource found

What is Moveworks?

Moveworks builds workplace assistants that search company knowledge and complete employee requests across business systems.

030 · foundationsSource found

What is n8n?

n8n develops a visual workflow-automation platform that can connect AI agents to applications, data, and fixed business steps.

031 · foundationsSource found

What is NVIDIA?

NVIDIA supplies chips, models, simulation tools, and software for training and running AI systems, including agents and robotics.

032 · foundationsSource found

What is OpenAI?

OpenAI develops the GPT model family, ChatGPT, Codex, APIs, and tools for creating and operating agents.

033 · foundationsSource found

What is Oracle?

Oracle adds AI assistants and agents to its cloud, database, and enterprise-application products.

034 · foundationsSource found

What is Patronus AI?

Patronus AI makes evaluation and security tools for finding failures in language models and agent systems before deployment.

035 · foundationsSource found

What is Portkey?

Portkey provides a gateway, observability, guardrail, and management layer for applications that call models and run agents.

036 · foundationsSource found

What is Protect AI?

Protect AI develops security tools for scanning models, dependencies, and machine-learning systems for exploitable risk.

037 · foundationsSource found

What is Pydantic?

Pydantic maintains Python validation tools and Pydantic AI, a framework for typed agent applications.

038 · foundationsSource found

What is Robust Intelligence?

Robust Intelligence developed testing and protection software for AI models; Cisco acquired the company, so current offerings should be checked there.

039 · foundationsSource found

What is Salesforce?

Salesforce develops Agentforce and related data, automation, and customer-management tools for business agents.

040 · foundationsSource found

What is SAP?

SAP builds Joule and agent tools that work inside finance, supply-chain, human-resources, and other business processes.

041 · foundationsSource found

What is ServiceNow?

ServiceNow develops AI agents for completing work across service, employee, customer, and technology-management workflows.

042 · foundationsSource found

What is Sierra?

Sierra builds customer-facing agents that can answer questions, make decisions, and take actions for brands.

043 · foundationsSource found

What is Skyvern?

Skyvern builds browser agents and automation infrastructure for completing work on websites through visible interface actions.

044 · foundationsSource found

What is UiPath?

UiPath combines robotic process automation, orchestration, and AI agents for structured work across company systems.

045 · foundationsSource found

What is Vapi?

Vapi provides developer infrastructure for building voice agents that handle live telephone conversations and use external tools.

046 · foundationsSource found

What is Writer?

Writer develops an enterprise AI platform for creating agents, applications, and governed workflows on company data.

047 · foundationsSource found

What is Zapier?

Zapier connects apps through automation and offers AI agents that can carry out work across those connections.