Revdoku makes agent email an integration decision
Revdoku has put inbound email, attachments, and agent access behind REST, CLI, and hosted MCP; that turns a familiar inbox into an integration surface rather than an isolated channel. The same control-plane question appears in Composio’s new emphasis on user-scoped authentication, sandboxed execution, and auditability, while Upsolve is bringing governed, logged data-agent calls into Claude. These are distinct products, but they point to the operational boundary worth reviewing: where agents receive unstructured input, which credentials they inherit, and what record remains. Map inbox access and tool-call logging before granting an agent a production mailbox.
See what changed on Revdoku's listing →
What changed on the ground
Changes we detected on each tool's own pages — pricing, features, platform reach — via our daily crawls. Often ahead of any press coverage; each links to the scored listing.
|
10/36 · Guided Assistant
Robutler launches a free, remixable agentic app platform with creator rewards — Robutler has substantially repositioned its product around free, pro-grade apps that users can remix with AI, connect to existing assistants and coding agents, collaborate on with humans and agents, and publish for usage-based Creator Rewa…
Source: the tool's own site — detected 2026-10-04 by agentic.ai's daily recrawl.
|
|
8/36 · Guided Assistant
Revdoku adds agent email inboxes, hosted MCP, and expanded API workflows — Revdoku now presents dedicated inbound email inboxes for AI agents and applications, with messages and attachments accessible through REST, CLI, and hosted MCP.
Source: the tool's own site — detected 2026-10-04 by agentic.ai's daily recrawl.
|
|
9/36 · Guided Assistant
Inworld AI acquires Ultravox and expands its realtime voice AI platform — Inworld AI now says it has acquired Ultravox to accelerate speech-to-speech research and voice-agent capabilities.
Source: the tool's own site — detected 2026-10-04 by agentic.ai's daily recrawl.
|
|
19/36 · Domain Specialist
Perplexity Computer adds Effort Mode, GPT-6 Astra, Skills Marketplace… — Perplexity’s Computer changelog now highlights several concrete product expansions, including adjustable effort levels, GPT-6 Astra support, reusable skills, hybrid cloud/local execution, Side Chat, and support for AMD-powered agentic PCs.
Source: the tool's own site — detected 2026-10-04 by agentic.ai's daily recrawl.
|
|
10/36 · Guided Assistant
Composio repositions as agent infrastructure for governed tool execution — Composio has substantially overhauled its product positioning, presenting itself as infrastructure for AI agents with user-scoped authentication, sessions, sandboxed and governed tool execution, auditability, and enterprise deployment opti…
Source: the tool's own site — detected 2026-10-03 by agentic.ai's daily recrawl.
|
|
13/36 · Guided Assistant
Upsolve launches MCP integration for Claude with governed, logged data-agent… — Upsolve’s updated site announces Upsolve MCP for Claude, allowing teams to use the same governed data agent, context, and permissions inside Claude while logging every call.
Source: the tool's own site — detected 2026-10-03 by agentic.ai's daily recrawl.
|
What's new in the directory
|
8/36 · Guided Assistant
VoiceDrop is a cloud platform for sending ringless voicemail campaigns and following up through two-way SMS. Sales teams can use cloned or library AI voices, upload contacts, schedule delivery, and route callbacks to an AI inbound agent.
Source: published listing, rubric-scored on ingest.
|
|
19/36 · Domain Specialist
Tale is a collaborative project workspace that combines task planning, AI-agent delegation, shared knowledge, and workflow automation. Teams can self-host it or use managed hosting, configure agents with supported runtimes and tools, and review work through approval and audit controls.
Source: published listing, rubric-scored on ingest.
|
|
3/36 · Reactive Tool
WellWired is a beginner-focused AI learning site for over-50s and older adults. It explains AI in plain English, offers practical guided exercises, and includes free tools for spotting potential scams.
Source: published listing, rubric-scored on ingest.
|
Agenticness Leaderboard
This week's most-clicked tools, re-ranked by rubric score. The score is the editorial signal; the popularity is what drew the directory's traffic here this week.
- Hyper · 22/36 · Domain Specialist · L3
Hyper is a cloud-based autonomous software engineering platform for turning product objectives into tested code in your GitHub repositories. It plans work, runs parallel agent sessions in isolated lanes, verifies results server-side, and can open pull requests or deploy supported projects.
- Cursor · 18/36 · Adaptive Collaborator · L2
Cursor is a developer-focused AI environment that adds agents, context, and automation around your repositories. It combines an editor-like interface, a CLI, and a cloud agent API to automate code review, bug fixing, CI hygiene, and more. Designed for individual developers and engineering teams who want AI to take real actions in their code and infrastructure, not just chat.
- Pacvue · 6/36 · Guided Assistant · L1
Pacvue is an AI-powered commerce media OS for retail media teams managing campaigns across marketplaces, search, and social. It helps you turn retail signals into measurable outcomes and ties media execution to performance insights.
CoCounsel is Thomson Reuters’ AI assistant for professionals in legal, tax, audit, and accounting. It connects to trusted content and existing workflows to help you research, review, and draft faster.
WHOOP is a health and fitness wearable that tracks sleep, strain, recovery, and heart health around the clock. It’s aimed at people who want ongoing guidance, not just raw fitness data.
Learn: How AUX actually works
AUX is a cloud API for verification, not for planning or acting on its own. You give it a business counterparty, and it pulls bounded evidence from sources like GLEIF, OFAC, IANA RDAP, and any private attestations you’ve configured. It then packages that evidence into signed bundles plus certification receipts. Another system is meant to read those outputs and decide what to do next. The description doesn’t say AUX keeps long-lived session state or takes autonomous actions beyond the check itself. So its job is narrow: gather proof, sign it, and hand control back to the caller for the real decision.
See AUX's full scorecard →
One tool worth testing
Tale — Test Tale for project teams that want to delegate planning and workflow work to agents without losing human review. It is a useful test now because its workspace combines agent delegation with approval and audit controls—the same operating concerns raised by today’s infrastructure changes—and it offers self-hosted or managed deployment. In a 30-minute pilot, run one existing planning workflow through Tale and compare approval steps, audit visibility, and deployment fit with your current workspace.
Our pick: Claude Code
The use case: coding agents.
Tops our independent /36 — the tiebreaker over Cursor: Continuity 3 vs 1. Pricing: Per-seat (usage per member, NOT pooled).
Ranked by our 9-dimension Agenticness rubric — not by who pays us. The full scorecard, true-cost pricing, and the reliability evidence behind every score are in the report.
Read the full report →
|