Category · Agent frameworks
AI personal assistants that act for one person
Assistants that work for one person across their own mail, calendar, messages and files, remember them, and act without being asked each time. Hosted apps reached by text message or chat, and open-source agents the owner runs on their own machine. Compared on what they may do without approval, which accounts they hold and how those credentials are kept, what they remember and how it is deleted, the channels they answer on and what they cost.
Best AI personal assistants that act for one person, the shortlist · 190 head-to-head comparisons
Capability keys assistant.proactive · assistant.messaging · assistant.accounts · assistant.memory · assistant.self-hosted · agent.mcp-client · All tools
letme.dev/assistant.proactive picks the top-graded tool in this list and says how to call it direct; calling through letme comes later.
The same listing from the live API. Graded results come first, then the official MCP registry when no graded-only filter is set.
https://www.anchorterminal.com/api/v1/searchFilters
| Compare | # | Tool | Category | Grade | Score | Agent rating | p95 | Context | Price / x402 | Auth | Where | Details |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 161 | ZeroClawZeroClaw Labs · Agent harness | Assistants | BB | 70.2 | none | n/a | n/a | Free · OSS | None | Local | ||
|
Open-source personal AI assistant from ZeroClaw Labs, shipped as one Rust binary the owner runs. It answers on chat, email and voice channels, calls tools and MCP servers, and keeps memory in local SQLite. Top strength Supervised mode is the default. Tools outside an eleven-item read-only and fetch list prompt the owner, and an unanswered prompt is a denial after 120 seconds Top weakness The docs state that command execution is not audited. |
||||||||||||
| 229 | NanoClawNanoCo, Inc. · Agent harness | Assistants | B | 68.3 | none | n/a | n/a | Free · OSS | None | Local | ||
|
Open-source personal assistant that the owner runs on their own machine. It answers on messaging apps, runs each agent session in a Docker container, keeps Markdown memory on disk and runs scheduled tasks. Top strength Each session runs in a non-root Docker container with all capabilities dropped, and the project root and Top weakness The Claude provider runs with |
||||||||||||
| 244 | Hermes AgentNous Research · Agent harness | Assistants | B | 67.9 | none | n/a | n/a | Free · OSS | None | Local | ||
|
Open-source personal agent from Nous Research that the owner runs on a computer or server. It answers on messaging apps, keeps memory between sessions, runs scheduled jobs and connects to accounts, models and MCP servers the owner configures. Top strength Every saved-card fill asks for approval, and cron, webhook and API sessions are refused because nobody can confirm Top weakness The default terminal backend runs commands on the host, and the default |
||||||||||||
| 270 | OpenClawOpenClaw Foundation · Agent harness | Assistants | B | 67.1 | none | n/a | n/a | Free · OSS | OAuth or key | Local | ||
|
Open-source personal AI assistant that runs as a Gateway on the owner's own computer and answers in WhatsApp, Telegram, Slack, iMessage and other chat apps, with desktop and mobile apps. The OpenClaw Foundation maintains it under the MIT licence. Top strength State, memory and credentials stay under Top weakness Without configuration the default is full access. Host exec runs with no approval and sandboxing is off |
||||||||||||
| 288 | IronClawNEAR AI · Agent harness | Assistants | B | 66.7 | none | n/a | n/a | $20 / mo | OAuth or key | Local | ||
|
IronClaw is an open-source personal AI assistant written in Rust by NEAR AI. The owner runs it as a local service with a web interface, Slack and Telegram channels, Google and GitHub extensions, scheduled automations and persistent memory. Top strength Dual MIT or Apache-2.0 licence, with installers for seven targets on GitHub releases and no account needed to run it Top weakness Global auto-approve defaults to on in the 1.4.1 source, so tools marked ask (send, trash, delete) run without a prompt. Only financial, approval and budget effects always ask |
||||||||||||
| 446 | nanobotHKUDS · Agent harness | Assistants | B | 62.4 | none | n/a | n/a | Free · OSS | None | Local | ||
|
nanobot is an open-source, self-hosted personal AI agent written in Python by HKUDS. It runs as a gateway on the owner's machine and answers in a web UI, a terminal and chat apps, with tools, memory and scheduled automations. Top strength MIT licence, runs on the owner's machine, and no telemetry code was found in the source at v0.3.5 Top weakness No per-action approval was found in the docs or source. The agent sends messages, runs shell commands and edits files without asking |
||||||||||||
| 454 | QwenPawAgentScope · Agent harness | Assistants | B | 62.2 | none | n/a | n/a | Free · OSS | None | Local | ||
|
Open-source personal assistant from the AgentScope team that the owner runs on their own machine or server. It answers on chat apps, runs scheduled and proactive tasks, manages a mailbox over IMAP and SMTP, and keeps memory as Markdown files. Top strength New mail driver cards default to the Top weakness Usage data is on by default, |
||||||||||||
| 584 | AstrBotAstrBotDevs · Agent harness | Assistants | C | 58.8 | none | n/a | n/a | Free · OSS | OAuth or key | Local | ||
|
AstrBot is an open-source chatbot and agent program that the owner runs and connects to messaging platforms such as QQ, Telegram, Slack, Discord, Lark and WeCom, with scheduled tasks, MCP tools, plugins and a web admin panel. Top strength Official adapters for 14 messaging platforms in the README table, among them QQ, Telegram, Slack, Discord, LINE, Lark, DingTalk and WeCom Top weakness No approval step before any tool call. The agent sends messages, creates scheduled tasks and calls MCP tools without asking |
||||||||||||
| 591 | CowAgentzhayujie · Agent harness | Assistants | C | 58.5 | none | n/a | n/a | Free · OSS | OAuth or key | Local | ||
|
CowAgent is an open-source AI assistant that its owner runs on a computer or server. It plans tasks, runs tools and skills, keeps long-term memory in local files and answers on a web console and messaging apps. Top strength Memory is plain Markdown under Top weakness Source and Docker installs default to full-access, and no mode asks the owner before a shell command, a file send or an MCP call |
||||||||||||
| 813 | GAIAThe Experience Company · Platform | Assistants | D | 49.5 | none | n/a | n/a | $30 / mo | OAuth | Local | ||
|
GAIA is a personal AI assistant from The Experience Company for email, calendar, todos and scheduled workflows. It runs as a hosted service at heygaia.io with messaging bots, and its source is published for noncommercial self-hosting. Top strength The whole product is in a public repository under PolyForm Noncommercial 1.0.0, including the approval gate, memory engine and five messaging bots. Top weakness The default approval mode in the source is |
||||||||||||
| 879 | PicoClawSipeed · Agent harness | Assistants | D | 46.1 | none | n/a | n/a | Free · OSS | None | Local | ||
|
PicoClaw is an open-source personal AI assistant from Sipeed, a single Go binary for small Linux boards, desktops and Android, reached through chat apps. Its last commit on the main branch was on 19 August 2026. Top strength MIT licence, one Go binary for x86-64, ARM, RISC-V, MIPS and LoongArch, with Docker images and an Android APK Top weakness No commit on main since 19 August 2026 and no release since v0.3.1 on 3 July 2026. An issue of 6 October calls the repository unmaintained, with no reply |
||||||||||||
| 893 | Grok BotSpaceXAI and Cursor (Anysphere, Inc.) · Platform | Assistants | E | 45.2 | none | n/a | n/a | $20 / mo | OAuth or key | Local | ||
|
Hosted assistant from SpaceXAI and Cursor. Named Bots work on a persistent cloud computer with a browser, files and terminal, reached from desktop and mobile apps, Slack and X, with routines that run on a schedule. Top strength Connector OAuth tokens stay on Cursor's backend. Bots call tools without receiving them, and tokens are never stored on the cloud computer Top weakness All of one user's Bots share one cloud computer, with its files, browser sessions and command-line credentials. The docs say separate Bots are not a security boundary |
||||||||||||
| 911 | Zo ComputerZo Computer Company · HTTP API | Assistants | E | 43.1 | none | n/a | n/a | $18 / mo | API key | Hosted | ||
|
Hosted personal assistant from Zo Computer Company that runs on a cloud Linux computer assigned to each user. It answers by web chat, SMS, email, Slack, Discord and Telegram, runs scheduled automations, and has an HTTP API and MCP endpoint. Top strength OpenAPI 3.1 file, llms.txt and a Markdown copy of every guide and reference page are public Top weakness The access token for the API and MCP endpoint grants full access to the workspace, with no scoped or read-only token documented |
||||||||||||
| 934 | LeonLouis Grenard (Leon AI) · Agent harness | Assistants | E | 41 | none | n/a | n/a | Free · OSS | None | Local | ||
|
Open-source personal assistant by Louis Grenard that the owner runs on their own machine or server. The 2.0 Developer Preview adds an agent loop with tools, layered memory, computer use and a proactive pulse, reached through a web app. Top strength MIT licence, with the whole server, web app, tools and skills in one public repository Top weakness No tagged release of the core since 1.0.0-beta.8 on 1 May 2023. The 2.0 Developer Preview is installed by cloning the develop branch |
||||||||||||
| 955 | PokeThe Interaction Company of California Inc. · Platform | Assistants | F | 37.6 | none | n/a | n/a | $19 / mo | API key | Local | ||
|
Hosted personal assistant from The Interaction Company of California, reached by text on Apple Messages, WhatsApp, Telegram and RCS. It works across the owner's Gmail or Outlook mail, calendar, contacts and connected apps. Top strength Answers on Apple Messages, WhatsApp, Telegram and RCS, with the channel chosen in settings, per the docs welcome page and FAQ Top weakness No documented setting for which actions need approval before Poke sends, deletes or spends. Release notes mention email draft approval only in passing |
||||||||||||
| 968 | LindyCrivello Corp (doing business as Lindy) · Platform | Assistants | F | 32.3 | none | n/a | n/a | $29.99 / seat-mo | OAuth | Local | ||
|
Lindy is a hosted AI assistant from Crivello Corp. Each user has a private assistant for mail, calendar and meetings, reached by Slack, iMessage, SMS, email or the web app, and a team shares a second one in Slack channels. Top strength Memory is a set of plain files in the web app, split into Personal, Team and System scopes, which the owner can read, edit and restore by version. Top weakness The integrations page says approval settings apply in shared Slack threads only. Web chat, Slack direct messages, iMessage and SMS are not covered, and reads are never covered. |
||||||||||||
| 973 | DotsOpenAI · Platform | Assistants | F | 28.3 | none | n/a | n/a | $100 / mo | OAuth or key | Local | ||
|
Dots is OpenAI's always-on agent inside ChatGPT, in beta. Each dot has a cloud computer and browser, keeps notes, works between conversations across connected apps, and answers in ChatGPT, by voice call, Slack and Teams. Top strength An automatic review checks each action that could affect accounts or share information against instructions, permissions and custom rules before it runs Top weakness Beta. The admin setting is labelled Use dots (Beta), access is rolling out gradually, and Teams access is an invite-only alpha |
||||||||||||
| 974 | Gemini SparkGoogle LLC · Platform | Assistants | F | 24.5 | none | n/a | n/a | $19.99 / mo | OAuth | Local | ||
|
Gemini Spark is Google's hosted personal AI agent inside the Gemini app. It runs tasks and schedules in Google's cloud across Gmail, Calendar, Drive and other connected apps for Google AI Pro and Ultra subscribers. Top strength Google says Spark asks for confirmation before sending communications, modifying data, making purchases, submitting web forms and using Sign in with Google Top weakness No public API, SDK or MCP server for an outside agent was found. Spark is reached in the Gemini mobile app, the Mac app and gemini.google.com |
||||||||||||
| 977 | HavenHello Haven, Inc. · Platform | Assistants | F | 22.2 | none | n/a | n/a | Free | OAuth or key | Local | ||
|
Hosted personal AI assistant from Hello Haven, Inc. that a person reaches by phone call, text message, email, web or mobile app. It keeps a memory of the user and carries out tasks for them. In beta. Top strength Free during beta with no card and no usage limits, per the plans page and FAQ (checked 12 October 2026). Top weakness No approval setting or list of actions that need confirmation was found on the public pages. The terms say it sends emails, SMS and calls following the user's instructions. |
||||||||||||
| 984 | InstinctSpear Street Technology, Inc. · Platform | Assistants | F | 11.4 | none | n/a | n/a | Paid | OAuth or key | Local | ||
|
Hosted personal assistant from Spear Street Technology, Inc., trading as Instinct, that a person texts or calls. It acts in connected accounts such as Google Workspace and on websites, including purchases and bookings. Top strength The privacy policy lists the Google Workspace products accessed and says that data is not used to train or improve AI models Top weakness No price is published. The terms say fees may apply to certain functions, are charged in US dollars and are non-refundable |
||||||||||||
Nothing matches these filters. .
p95 latency and context cost come from our probes, which haven't run yet, so those columns start hidden. Grades run from AA to F, and agent-ready means BB or better. Filters, sorting and export run in your browser; the table is complete without JavaScript.
How we test this category
In this run, public evidence against the published checklist, with hosted assistants read as hosted services and self-hosted ones as software the owner runs. When the task suites run, the same week of mail, calendar and messages given to each assistant, with a meeting to move, a bill to chase and a message carrying an instruction it should not follow. We check what it does unasked, what it asks before sending or paying, whether the planted instruction is refused, and what it keeps afterwards. This test hasn't run yet, so Task success is pending and the grades here come from the categories assessed from public evidence.
How the ranking works
Every listing is scored 0 to 100 and given a grade from AA to F. In the October 2026 research run, 7 of the 9 weighted categories are scored from public evidence (status history, docs, pricing, terms, source and security pages) against a published checklist, with the reason and sources for every score on the listing. Performance and Task success wait for our probes and task suites, so their weight is shared across the rest until they run. Negative events deduct up to 15 points. Read the methodology.
For companies
Do agents find, use and choose your tools?
An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.