mercury-agent

Open-source background agent with local memory, permission rules and chat access from many apps.

IndexedMIT★ 3,465

Chalk Labs

Need help deploying mercury-agent?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Get started

Setup steps are in the repository. Website · Repository

About

Mercury is an open-source personal AI agent that runs as a background process on the user's machine, with a personality the user writes, a memory kept on local disk and a permission system between the model and the machine. Users reach the same agent from a terminal UI, Telegram, Discord, Slack, Signal or a local web dashboard. It reads and writes files, runs commands, works with git and GitHub, researches the web and keeps schedules, with a shell blocklist, folder scopes and approval prompts. Supported models include DeepSeek, OpenAI, Anthropic, Grok, Ollama and LM Studio, and each day's usage stays within a token budget.

Use cases: personal-assistant, coding, research, workflow-automation, team-chat, code-generation

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Fact sheet

Jobs: personal assistant, coding, researchREADME
Autonomy: Supervised: runs multi-step tasks, asks at checkpointsREADME
Where you use it: Terminal, Web, Slack, otherREADME
Hosting: You run itREADME
Models: deepseek, openai, anthropic, xai, ollama, lm-studioREADME
Interfaces: agent-skillsREADME
Open source: YesREADME

Facts extracted by Claude Haiku 5.5 from the linked sources on Oct 24, 2026. Wrong fact? Tell us.

Built on

Frameworks named in its dependency files.

0.727score
Vercel AI SDK
Vercel
TypeScript toolkit for AI apps and agents with a unified provider API, streaming, UI hooks and a wrapper for running established agent harnesses.
HarnessAFreshness: A★ 27.5K

Signals

Stars: 3,465
Forks: 355
Open issues: 15
Last commit: Oct 24, 2026 (6 days ago)
Last release: Oct 24, 2026 (6 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License: MIT
Repository: github.com/cosmicstack-labs/mercury-agent
Website: mercuryagent.sh/
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: README github-graphql

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped: 50+; launches shipped
media placements: 500+; media placements
founders on every account: 2; founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get mercury-agent running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Need help deploying mercury-agent?

Call Get help

Cite this page

mercury-agent. Agent Mart. https://agentmart.dev/agents/mercury-agent (last updated 2026-10-24)