Skip to content
repository radar
Agents & Orchestration

🔍AgenticSeek

ACTIVE BREAKOUT

Fosowl/agenticSeek · homepage ↗

Fully Local Manus AI. No APIs, No $200 monthly bills. Enjoy an autonomous agent that thinks, browses the web, and code for the sole cost of electricity.

⭐ Very popular: 27k stars, gaining about 90 a week

View on GitHub ↗

repo profile

vintage 2025 1 year old
language Python
license GPL-3.0

momentum

total stars 27k
stars added last week +90
HN peak 122 pts 1y 3mo ago
commits / week 1 cooling · -69% vs prior mo
issues closed 52% ~14d to close, median
contributors 49 (+1 in 15d)
release cadence n/a
last activity 4d ago

durability

backing community / independent
openness copyleft
bus factor 2 concentrated
top-author share 41% 6 mo

bus factor = how many people it takes to cover more than half the commits (6 months). 1 is a solo project; higher means the work is spread across a team. top-author share is the single busiest author's slice of those commits.

since we covered it

monthly average + 1k/mo (+22%/mo) · + 21k total since PR#9

why it's a big deal

  • Runs an autonomous agent that browses the web, generates code, and plans tasks entirely on local hardware, so no data leaves the machine and there are no API costs.
  • Positions itself as a local alternative to Manus AI for users who want agentic behaviour without a cloud provider, trading recurring fees for a one-time GPU requirement.
  • Model quality scales with hardware, with the maintainers noting 7B models hallucinate frequently and 32B or larger on 24GB VRAM is needed to handle most tasks reliably.

under the hood

  • Python backend split across a REST API server, a CLI, and an llm_router provider abstraction, with a JavaScript and React frontend served at localhost:3000.
  • Ships via Docker Compose bundling SearxNG for local search, Redis for caching, and ChromeDriver for browser automation, requiring Python 3.10 and Docker Engine.
  • Supports local inference through Ollama, LM Studio, and OpenAI-compatible servers, plus optional API backends including OpenAI, Gemini, Deepseek, and OpenRouter, with an llm_server component for running the model on a separate machine.

Radar summary, generated from the project's public sources

star history

PR#9 · 6k27k now Feb 2025Aug 2026
  1. PR#9 6k 2025-05-28
  2. now 27k + 21k since first covered

curve is sampled from GitHub's star history, plus our own daily readings since we covered it; the dashed stretch is before we first covered it, the solid line since. figures at coverage are the numbers we printed then (approx.), current count is live.

understory

Output and attention are roughly in balance.

-10 understory score output 47 · clout 57
Aug 2025 Jul 2026
  • output, commits & releases
  • clout, star velocity

output = commits & releases; clout = star velocity, both 0 to 100 monthly indices; the gap where output runs above clout is the understory. The understory →

covered in

  • PR#9 2025-05-28 below the radar

    Fully Local AI Agent with Autonomous Web & Code Capabilities

similar projects

compare these →
  • 📚 Haystack

    Apache-2.0 licensed

    Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.

    26k ACTIVE
  • 🎛️ CopilotKit

    TypeScript · MIT licensed

    The Frontend Stack for Agents & Generative UI. React, Angular, Mobile, Slack, and more. Makers of the AG-UI Protocol

    37k ACTIVE
  • 🔗 Composio

    TypeScript · MIT licensed

    Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to help you build AI agents that turn intent into action.

    30k ACTIVE

comments

Sign in with GitHub to add your blip on AgenticSeek.

loading comments…