Toolbox/Applied agents

Personal assistants

assistants and chat-based task agents

25 repositories, most starred first
State of the category

NousResearch/hermes-agent NousResearch/hermes-agent is the clear leader — the most-starred, full-featured, self-hostable personal agent with a built-in closed learning loop; pick it if you want an out-of-the-box, persistent, self-improving assistant you can run yourself. Expect many alternatives because teams need different tradeoffs around privacy, size, UIs, vertical workflows, and extensibility that Hermes does not optimize for.

On-device privacy
Teams that must keep data—and models—on-prem or local need projects that prioritize fully local runtimes and offline inference to avoid third‑party exposure.
Lightweight runtimes
Many teams need minimal, readable, embeddable agent engines or tiny CLIs that are easy to audit, integrate, and run on constrained hosts instead of a heavy platform.
Vertical workflows
Organizations building domain-specific tasks (recruiting, teaching, travel planning, habit nudges, fantasy management) need agents tailored to those end‑to‑end flows rather than a generalist core.
Rich UIs & integrations
Product teams often need polished desktop/mobile apps, avatars, multimedia output, or hardware integrations that make assistants practical for end users rather than only dev tooling.
Extensibility & safety
Teams that require sandboxing, plugin ecosystems, model routing, multi‑agent kernels or eval/tooling want modular platforms that make building, testing, and securing custom skills easier than a single monolith.
Find your fit

Which one matches your setup?

Answer any of the questions — the shortlist updates as you go. Recommendations come from the capability passports below, nothing else.

Where should reviews happen?
Can code leave your infrastructure?
What matters most?
Model access?
Pick at least one answer to get a shortlist.
Side by side

Comparison matrix

Axes are extracted from each project's docs by our review pipeline; the maturity score is computed from stars, growth and commit activity — not an opinion. Click a column to sort.

Runs inModelsContextCost to run
241.2k +3638/7d
CLIWeb appBYOKOpenAIAnthropicRelated filesApproval & allowlistSelf-hostableYour API key or Nous Portal subscription
53.9k +299/7d
CLIWeb appBYOKOpenAIAnthropicGeminiOllama / localDiff/File onlyNone mentionedSelf-hostableYour API key for cloud models; can use local models.
47.7k +220/7d
CLIWeb appBYOKAnthropicOllama / localDiff + related filesBasic filters/configFully local possibleYour API key; optional paid hosting
40.7k +3258/7d
CLIAnthropicFixed providerRepo + documentsReviewer + dedupeThird-party cloudRequires Claude Code (Anthropic) CLI / third‑party access.
38.7k +918/7d
CLIWeb appBYOKOpenAIAnthropicGeminiOllama / localMulti-doc RAGBasic filtersFully localFree to self-host; uses your model API key or local LLMs
34.9k +283/7d
CLIWeb appIDEBYOKOllama / localFixed providerDiff + related filesApproval gates & guardsRuns fully localLocal runtime free; can use your cloud API keys if configured.
5.9k +41/7d
CLIFixed providerConversation onlyNo noise controlsSelf-hostableFree to download, local runtime.
1.1k +115/7d
CLIWeb appBYOKOpenAIAnthropicOllama / localContext pack + recallThreshold gatingFully local possibleYour API key (per-provider) or run local models
1.9k +35/7d
CLIOpenAIWhole-repo analysisConfig & normalizationLocal tool + cloud LLMsYour API key (OpenAI recommended)
1.7k +73/7d
CLIWeb appBYOKOpenAIAnthropicGeminiFixed providerRelated filesGate + evalsSelf-hostableYour API key; provider billing applies
1.2k +9/7d
CLIOllama / localFixed providerRelated files & skillsBasic filters & promptsFully localFree/local models; optional remote provider costs
1.5k
Web appBYOKOpenAIAnthropicOllama / localSession-only contextDedup & filtersSelf-hostableYour API key; optional NagaModel gateway
Ranked by maturity — 13 more in the full catalog below.
At a glance

Capability profiles

Six axes, 0–5 each. The shape tells you the strategy: a wide hexagon is a generalist, a spike is a specialist. Showing the 8 most established — the rest are in the full catalog.

ContextNoiseCustomPrivacyModelsMaturity

A self-hostable personal agent with a built-in closed learning loop that creates, persists, and self-improves skills from its own experience.

ContextNoiseCustomPrivacyModelsMaturity

A native, local-first agent with desktop app, CLI, and an extensible plugin ecosystem (Model Context Protocol) plus broad provider support.

HKUDS/nanobot47.7k
ContextNoiseCustomPrivacyModelsMaturity

An ultra-lightweight, self-hosted personal agent runtime that pairs a small, readable core with built-in WebUI, persistent memory, automation, and flexible model routing for long-running workflows.

ContextNoiseCustomPrivacyModelsMaturity

Local-first, end-to-end job-application framework that scrapes portals, tailors LaTeX CVs/cover letters, runs a drafter–reviewer agent pipeline, and archives applications for repeatable, owned job hunting.

ContextNoiseCustomPrivacyModelsMaturity

A self-hostable, multi-agent tutoring platform with built-in RAG, three-layer persistent memory and a pluginable Skills ecosystem for lifelong personalized learning.

ContextNoiseCustomPrivacyModelsMaturity

Local-first Agent OS with built-in local models, three-layer self-evolving memory (ReMe), and kernel-level sandboxing for secure, extensible personal assistants.

ContextNoiseCustomPrivacyModelsMaturity

A personality-first, lifelike QQ chatbot that emphasizes human-style conversation and long-term user modeling while offering an extensible plugin/event system.

ContextNoiseCustomPrivacyModelsMaturity

Three-layer memory (learner profile, native wiki, cross-session recall) plus a proactive scheduler and a workspace Practice Lab — an education-optimized, evidence-driven agent design layered on the Pi SDK.

All repositories (25)

The agent that grows with you

241.2k
+3,6387d
Python
1 yr

an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with…

53.9k
+2997d
Rust
2 yrs

Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, M…

47.7k
+2207d
Python
7 mo

The job search that runs on your machine. AI job application framework built on Claude Code: evaluate postings…

40.7k
+3,2587d
Python
5 mo

DeepTutor: Lifelong Personalized Tutoring. https://deeptutor.info/.

38.7k
+9187d
Python
8 mo

Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple cha…

34.9k
+2837d
Python
6 mo

MaiSaka, an LLM-based intelligent agent, is a digital lifeform devoted to understanding you and interacting in…

5.9k
+417d
Python
1 yr

把岗位描述变项目,把项目变简历,把简历变面试。

1.9k
+357d
Python
3 mo

Waku Waku! Waku Agent is a local-first AI agent harness you actually own, including loop, memory, eval, all in…

1.7k
+737d
Python
1 mo

A simple yet powerful agent framework for personal assistants, designed to enable intelligent interaction, mul…

1.5k
-27d
Python
1 yr

PhoneClaw turns phones into local AI agent runtimes with on-device models, native mobile Skills, LiveLand, and…

1.2k
+97d
Swift
5 mo

An open-source personal learning agent with three-layer memory (learner profile / wiki knowledge base / cross-…

1.1k
+1157d
TypeScript
3 mo

Agent-led job application workflow with a local progress-tracking dashboard — works with any AI coding agent t…

718
+1277d
HTML
1 mo

Smart Promise Tracker AI 2026 – Commit Memory Engine

129
+17d
HTML
2 mo

Open Source AI Expert Agent Bridge for Cursor 2026

116
HTML
2 mo

Panel-based personal assistant with a plugin architecture for productivity workflows. AI agents share a worksp…

91
+17d
TypeScript
7 mo

Lightweight local swappable semantic search & ask CLI agent for Gmail

74
+17d
Python
1 yr

CLI agentにpavlokを使用させたらどうなるか自傷実験

71
Python
8 mo

A travel planning Agent powered by LangGraph, Amap POI, route clustering and LLM-based itinerary generation.

66
-17d
Python
3 mo

Open source CLI agent that generates complete lesson bundles in your teaching voice. 48+ tools, zero-touch 9-f…

58
+17d
TypeScript
5 mo

Local-first AI desktop assistant that scrapes job boards, matches roles to your resume, and auto-generates res…

54
+17d
Rust
3 mo

Assessment-driven, local-first learning agent built on an observable Agent Runtime and eval harness—grounded i…

33
Python
2 mo

🪼 A personal AI assistant that lives in Telegram — every topic is its own isolated Claude Code agent with lay…

30
-17d
TypeScript
3 mo

Ask your video library anything — an AI agent that watches, reasons in a tool-use loop, and answers with playa…

29
Python
4 mo

Agente autónomo para LALIGA Fantasy: lee el juego, decide y actúa (pujas, ventas, clausulazos, alineación). Py…

22
+27d
Python
3 wk
Don't want to self-host?

Hosted alternatives

If running your own reviewer is more ops than you want, these managed services cover the same job.

Lindy

A hosted personal-assistant builder: wire up email, calendar and messaging agents from templates and let Lindy run them, instead of keeping a bot process alive yourself.

Try Lindy
Cognosys

A managed autonomous assistant for research, scheduling and recurring tasks — the same everyday-agent idea, run in the cloud with no self-hosting.

Try Cognosys

More in Applied agents