Catalog changelog # What changed, and when. 112 systems · 89 vendors. Every inventory change is recorded here — also as [RSS](https://www.agentlist.io/feed.xml) and [JSON](https://www.agentlist.io/api/v1/changelog). 2026-09-26 ## 2026-09-26 - added Cursor Origin + Grok Voice Agent API — Cursor Origin (sys://anysphere/cursor-origin) — Anysphere's agent-first code hosting and PR platform, first verified platform entry. Grok Voice Agent API (sys://xai/grok-voice) — xAI's speech-to-speech voice platform with telephony and a no-code builder. Cursor added as a dev-tool integration target. - added Icon index + /icons gallery — All 199 agent and vendor marks resolved from each homepage's declared icons (apple-touch-icon, favicon) and GitHub org avatars — browseable and copyable at /icons, served as JSON at /api/v1/icons, and now rendered across cards and spec sheets via the curated index. - milestone Transports registry — the wires agents actually speak — New /transports section maps the channels and wire protocols agents communicate over: agent wire protocols (MCP, A2A, AGNTCY/SLIM, ANP, ACP, AG-UI, AITP), messaging channels (Slack, Telegram, Discord, WhatsApp, Signal, iMessage, email), remote access (SSH, mesh VPNs like Tailscale, HTTPS tunnels, webhooks), and realtime media (PSTN/SIP, WebRTC) — each with the cataloged systems that speak it, tagged only where documented. Exposed at /api/v1/transports and as a 'Speaks' row on every spec sheet. 2026-09-25 ## 2026-09-25 - milestone Learn section — four interactive guides — New /learn section with two interactive guides: the Autonomy Dial (five delegation levels from suggests to holds-a-job, each grounded in live catalog exemplars) Which agent do you need? (a three-question quiz scored against the live catalog), Same task, different anatomy (one task traced through CLI/cloud/IDE/voice/ops agent anatomies with capability-tagged steps), and Anatomy of an MCP call (a 7-step walkthrough of a tool invocation crossing the JSON-RPC boundary). - milestone Capability taxonomy, vendor pages, integration matrix — New atomic capability taxonomy — 28 tags (file editing, browser operation, MCP tools, agent payments, identity, sandbox runtimes…) applied across all 110 systems, filterable in the index and browsable at /capabilities. New /vendors section profiles all 89 vendors with portfolio spec sheets and curated head-to-heads. New /integrations section maps which external systems each agent connects to — GitHub, Slack, Salesforce, Twilio, MCP servers — with the tail of each matrix gated 80/20. /api/v1/systems now exposes capabilities and integrations per system. - milestone Sixth expansion — agent services — New agent-services category covers the substrate agents can't self-provision: payments (x402, AP2, Skyfire, Payman, Nevermined, AgentCard), identity and delegated auth (Keycard, Arcade, Scalekit), tool platform (Composio), compute (E2B, Browserbase), and senses (Exa, Mem0). AgentMail recategorized from agent-communication — an inbox is a service, not a protocol. - added [x402 added](https://www.agentlist.io/systems/x402) — Coinbase's open protocol reviving HTTP 402 for stablecoin-settled machine payments. - added [Agent Payments Protocol added](https://www.agentlist.io/systems/ap2) — Google's signed-mandate spec for agent payments over existing rails. - added [Skyfire added](https://www.agentlist.io/systems/skyfire) — Agent wallets plus KYA identity — a payments network for the agent economy. - added [Payman added](https://www.agentlist.io/systems/payman) — Agent spend with policy limits and human-in-the-loop approval. - added [Nevermined added](https://www.agentlist.io/systems/nevermined) — Agentic-commerce infrastructure — payment plans and metering between agents. - added [AgentCard added](https://www.agentlist.io/systems/agentcard) — CLI-issued virtual cards, agent email, and x402 wallet in one package. - added [Keycard added](https://www.agentlist.io/systems/keycard) — Identity and policy control plane for autonomous agents. - added [Arcade added](https://www.agentlist.io/systems/arcade) — Delegated OAuth and prebuilt tools so agents act on a user's behalf. - added [Scalekit added](https://www.agentlist.io/systems/scalekit) — MCP/auth stack covering user SSO and agent credentials. - added [Composio added](https://www.agentlist.io/systems/composio) — 250+ SaaS tools exposed to any agent framework with managed auth. - added [E2B added](https://www.agentlist.io/systems/e2b) — Secure sandboxes where agents run untrusted code. - added [Browserbase added](https://www.agentlist.io/systems/browserbase) — Hosted headless browsers with stealth, sessions, and replay. - added [Exa added](https://www.agentlist.io/systems/exa) — Search index built for agents — meaning-based queries, clean contents. - added [Mem0 added](https://www.agentlist.io/systems/mem0) — Memory layer for agents — extract, store, retrieve across sessions. - updated [AgentMail recategorized](https://www.agentlist.io/systems/agentmail) — Moved from agent-communication to agent-services — an inbox is a service substrate, not an agent↔agent protocol. - milestone Fifth expansion — agent communication — New agent-communication category covers agent-to-agent work: open protocols (A2A, AGNTCY, ANP, NANDA), platforms and frameworks (BeeAI, CrewAI, Microsoft Agent Framework, LangGraph, MetaGPT, CAMEL, Agency Swarm, OpenAI Agents SDK, AgentMail); OpenScout / Scout recategorized from bridge. - added [A2A Protocol added](https://www.agentlist.io/systems/a2a) — Linux-Foundation open protocol for cross-vendor agent discovery and task exchange. - added [AGNTCY added](https://www.agentlist.io/systems/agntcy) — Cisco-originated 'Internet of Agents' stack — directory, SLIM messaging, identity. - added [Agent Network Protocol added](https://www.agentlist.io/systems/anp) — Decentralized agent messaging spec with DID identity. - added [NANDA added](https://www.agentlist.io/systems/nanda) — MIT Media Lab's Internet of AI Agents registry and index research. - added [BeeAI added](https://www.agentlist.io/systems/beeai) — IBM's open-source multi-agent platform with ACP/A2A interop. - added [CrewAI added](https://www.agentlist.io/systems/crewai) — Role-based multi-agent crews — the most adopted framework in the category. - added [Microsoft Agent Framework added](https://www.agentlist.io/systems/agent-framework) — AutoGen + Semantic Kernel successor for multi-agent graphs. - added [LangGraph added](https://www.agentlist.io/systems/langgraph) — LangChain's stateful graph runtime with supervisor and swarm patterns. - added [MetaGPT added](https://www.agentlist.io/systems/metagpt) — Multi-agent framework simulating a software company's assembly line. - added [CAMEL added](https://www.agentlist.io/systems/camel) — Research-rooted framework for role-playing agent societies. - added [Agency Swarm added](https://www.agentlist.io/systems/agency-swarm) — OpenAI-native agencies with explicit agent communication flows. - added [OpenAI Agents SDK added](https://www.agentlist.io/systems/openai-agents-sdk) — Lightweight agentic framework whose handoffs are first-class agent↔agent. - added [AgentMail added](https://www.agentlist.io/systems/agentmail) — Email infrastructure purpose-built for agents. - updated [OpenScout / Scout recategorized](https://www.agentlist.io/systems/scout) — Moved from bridge to agent-communication — agent-to-agent messaging is the product's core. 2026-09-24 ## 2026-09-24 - milestone Fourth expansion — agents beyond code — Five new categories widen the catalog past developer tools: digital employees (Alice, Ava, Piper, Sierra, Decagon, Fin, Harvey, Lindy, Juicebox, Mercor), ops agents (Cleric, Resolve, incident.io, Rootly, Bits AI, Dropzone, Simbian), computer-use agents (Browser Use, Skyvern, ChatGPT Agent, Claude Computer Use, Manus, Stagehand), research agents (ChatGPT/Gemini Deep Research, Perplexity, Genspark, Hebbia, Elicit, AlphaSense), and voice agents (Vapi, Bland, Retell, Synthflow, ElevenLabs Agents, Deepgram). New interfaces recorded: chat, browser, voice. Counts now 66 vendors / 83 systems / 13 categories. - added [Alice added](https://www.agentlist.io/systems/alice) — 11x's AI SDR — outbound email/LinkedIn prospecting plus Julian on inbound calls. - added [Ava added](https://www.agentlist.io/systems/ava) — Artisan's AI BDR — contact database, deliverability, and reply handling in one contract. - added [Piper added](https://www.agentlist.io/systems/piper) — Qualified's inbound AI SDR — website qualification and meeting routing, Salesforce-native. - added [Sierra added](https://www.agentlist.io/systems/sierra) — Customer-service AI employee for consumer brands; outcome-priced resolutions across chat and voice. - added [Decagon added](https://www.agentlist.io/systems/decagon) — Autonomous support agents with ops-team procedure controls (AOPs). - added [Fin added](https://www.agentlist.io/systems/fin) — Intercom's AI support agent; $0.99 per resolved conversation. - added [Harvey added](https://www.agentlist.io/systems/harvey) — AI associate for legal work — drafting, review, diligence over legal corpora. - added [Lindy added](https://www.agentlist.io/systems/lindy) — Build-your-own-employee platform — inbox, calendar, notes, and custom workflows. - added [Juicebox added](https://www.agentlist.io/systems/juicebox) — PeopleGPT recruiting agent — natural-language talent search plus outreach. - added [Mercor added](https://www.agentlist.io/systems/mercor) — AI interviewer and talent marketplace for high-volume screening. - added [Cleric added](https://www.agentlist.io/systems/cleric) — Dedicated AI SRE — investigates alerts and drafts root-cause hypotheses in Slack. - added [Resolve added](https://www.agentlist.io/systems/resolve) — AI SRE from observability veterans — triage, investigation, remediation drafts. - added [incident.io added](https://www.agentlist.io/systems/incident-io) — Incident platform with AI summaries, timelines, and similar-incident recall. - added [Rootly added](https://www.agentlist.io/systems/rootly) — Incident-response platform with AI-drafted summaries and retros. - added [Bits AI added](https://www.agentlist.io/systems/bits-ai) — Datadog's in-platform agent — natural-language observability and incident investigation. - added [Dropzone AI added](https://www.agentlist.io/systems/dropzone) — AI SOC analyst — end-to-end alert investigation with evidence chains. - added [Simbian added](https://www.agentlist.io/systems/simbian) — Autonomous SOC agents plus GRC automation. - added [Browser Use added](https://www.agentlist.io/systems/browser-use) — Breakout OSS browser-agent framework plus managed cloud. - added [Skyvern added](https://www.agentlist.io/systems/skyvern) — Vision-based open-source browser automation — no per-site selectors. - added [ChatGPT Agent added](https://www.agentlist.io/systems/chatgpt-agent) — OpenAI's hosted computer-use mode — Operator's successor inside ChatGPT. - added [Claude Computer Use added](https://www.agentlist.io/systems/claude-computer-use) — Anthropic's GUI-control API capability — screenshots in, mouse/keyboard actions out. - added [Manus added](https://www.agentlist.io/systems/manus) — Hosted general agent — cloud-sandbox tasks returning finished artifacts. - added [Stagehand added](https://www.agentlist.io/systems/stagehand) — Browserbase's OSS act/extract/observe framework — half scripted, half agentic. - added [ChatGPT Deep Research added](https://www.agentlist.io/systems/deep-research) — OpenAI's research-agent mode — long browsing runs returning cited reports. - added [Gemini Deep Research added](https://www.agentlist.io/systems/gemini-deep-research) — Google's research-agent mode with Workspace integration. - added [Perplexity added](https://www.agentlist.io/systems/perplexity) — Answer engine with Deep Research and Labs modes. - added [Genspark added](https://www.agentlist.io/systems/genspark) — Super Agent workspace — research that lands as pages, decks, and sheets. - added [Hebbia added](https://www.agentlist.io/systems/hebbia) — Matrix analyst agent for finance/legal over licensed and internal corpora. - added [Elicit added](https://www.agentlist.io/systems/elicit) — Research agent for scientific literature — extraction tables over 125M+ papers. - added [AlphaSense added](https://www.agentlist.io/systems/alphasense) — Institutional market-intelligence platform with Deep Research agents. - added [Vapi added](https://www.agentlist.io/systems/vapi) — API-first voice-agent orchestration — swap STT, LLM, TTS, telephony per call. - added [Bland AI added](https://www.agentlist.io/systems/bland) — Enterprise phone-agent platform with compliance posture. - added [Retell AI added](https://www.agentlist.io/systems/retell) — Voice-agent platform tuned for call quality — latency, barge-in, transfers. - added [Synthflow added](https://www.agentlist.io/systems/synthflow) — No-code voice agents — receptionists and outbound for SMBs and agencies. - added [ElevenLabs Agents added](https://www.agentlist.io/systems/elevenlabs-agents) — Voice agents on ElevenLabs' TTS stack — 70+ languages, phone and web. - added [Deepgram Voice Agent added](https://www.agentlist.io/systems/deepgram-voice-agent) — Speech-native unified endpoint for real-time voice agents. 2026-09-22 ## 2026-09-22 - milestone Third expansion — personal agents category — New category for self-hosted, chat-first assistant runtimes: OpenClaw and its fork family (NanoClaw, ZeroClaw, PicoClaw, nanobot) plus Nous Research's Hermes Agent. Counts now 34 vendors / 47 systems / 8 categories. - added [OpenClaw added](https://www.agentlist.io/systems/openclaw) — The self-hosted assistant gateway — ~29 chat channels, skills, memory, multi-agent routing; MIT, 501(c)(3)-stewarded. - added [Hermes Agent added](https://www.agentlist.io/systems/hermes-agent) — Nous Research's self-improving agent; learning loop, memory, seven backends incl. serverless. - added [NanoClaw added](https://www.agentlist.io/systems/nanoclaw) — TypeScript OpenClaw fork with container-per-agent isolation and Agent Swarms. - added [ZeroClaw added](https://www.agentlist.io/systems/zeroclaw) — Rust rewrite — single binary, ~5MB RAM, 30+ channels, hardware peripherals. - added [PicoClaw added](https://www.agentlist.io/systems/picoclaw) — Sipeed's Go build for embedded — <10MB RAM, <1s cold start on $10 boards. - added [nanobot added](https://www.agentlist.io/systems/nanobot) — HKUDS's small, auditable Python assistant; MCP-native tools. - milestone Second expansion — 9 systems added — New lab CLIs (Muse, Grok, Kimi, Qwen, Mistral), OSS agents (Crush, Kilo), JetBrains Junie, and the Instinct memory bridge. Counts now 28 vendors / 41 systems. - added [Muse Code added](https://www.agentlist.io/systems/muse-code) — Meta's terminal agent on Muse Spark 1.2; contributor tier free, API pay-as-you-go. - added [Grok Build added](https://www.agentlist.io/systems/grok-build) — xAI's open-source Rust TUI on Grok 4.6; free to try, bundled with SuperGrok / X Premium+. - added [Kimi Code added](https://www.agentlist.io/systems/kimi-code) — Moonshot AI's single-binary agent; multi-provider incl. Anthropic/OpenAI-compatible. - added [Qwen Code added](https://www.agentlist.io/systems/qwen-code) — Alibaba's OSS Gemini-CLI-derived agent; IDE plugins, desktop app, daemon, SDKs. - added [Mistral Vibe added](https://www.agentlist.io/systems/mistral-vibe) — Mistral's OSS CLI on Devstral 2; IDE extensions via ACP. - added [Crush added](https://www.agentlist.io/systems/crush) — Charm's multi-model terminal agent; OSS, BYO provider keys. - added [Kilo Code added](https://www.agentlist.io/systems/kilo-code) — Roo Code successor on a shared OpenCode engine; VS Code, CLI, and cloud agents. - added [Junie added](https://www.agentlist.io/systems/junie) — JetBrains agent, GA June 2026; IDE-native agentic debugging plus a terminal CLI. - added [Instinct added](https://www.agentlist.io/systems/instinct) — Self-learning memory MCP server for coding agents; OSS, MIT. - milestone Full inventory re-verification — All 32 entries re-checked against vendor pricing pages; counts moved to 20 vendors / 32 systems. - added [Roomote added](https://www.agentlist.io/systems/roomote) — Roo Code team's single-tenant cloud agent; self-host free ≤10 users, cloud from $49/mo. - added [Augment Code added](https://www.agentlist.io/systems/augment) — Context-engine coding agent; Business $100/mo flat up to 50 seats. - added [Warp added](https://www.agentlist.io/systems/warp) — GPU terminal with bundled agents; free tier has no agent usage, Pro $20/mo. - added [Trae added](https://www.agentlist.io/systems/trae) — ByteDance's AI-native VS Code fork; regional pricing differs. - added [Zed added](https://www.agentlist.io/systems/zed) — Fast Rust editor with BYOK; Pro $10/mo incl. $5 token credit. - added [Gemini CLI added](https://www.agentlist.io/systems/gemini-cli) — Consumer/free path ended 2026-06-18; API-key and Code Assist routes remain. - added [Google Antigravity added](https://www.agentlist.io/systems/antigravity) — Agent-first IDE; individual free tier, capacity via Google AI Pro/Ultra. - added [Kiro added](https://www.agentlist.io/systems/kiro) — AWS spec-driven IDE; free 50 credits, Pro $20/mo up to Power $200/mo. - retired [Roo Code retired](https://www.agentlist.io/systems/roo-code) — Extension shut down 2026-05-15; team moved to Roomote. - retired [Continue retired](https://www.agentlist.io/systems/continue) — Acqui-hired by Cursor ~June 2026; repo read-only, standalone product folded. - caution [Cody flagged active-caution](https://www.agentlist.io/systems/cody) — Consumer tiers ended; enterprise-only, no public price. - caution [Gemini Code Assist flagged active-caution](https://www.agentlist.io/systems/gemini-code-assist) — Free individual tier ended 2026-06-18. - updated [Cursor pricing refreshed](https://www.agentlist.io/systems/cursor) — Pro $20 / Pro+ $60 / Ultra $200; Teams Standard $40, Premium $120/user. - updated [Windsurf plans refreshed](https://www.agentlist.io/systems/windsurf) — Free / Pro $20 / Max $200; Teams ~$80 + $40/seat under Cognition. - updated [Devin plans refreshed](https://www.agentlist.io/systems/devin) — Free / Pro $20 / Max $200 / Teams $80 + $40 seat; old $500 Team plan retired. - updated [GitHub Copilot tiers refreshed](https://www.agentlist.io/systems/copilot) — Free / Pro $10 / Pro+ $39 / Max $100; Business $19, Enterprise $39/seat. - milestone Initial seed catalog — 14 vendors, 24 systems across 7 categories generated from first-pass inventory. --- Source: [Catalog changelog — what changed in the agent inventory | agentlist.io](https://www.agentlist.io/changelog). This is the public page rendered as Markdown; interactive controls require the website.