Data and AI agents

8,830 tagged Data and AI, measured the same way as everything else here.

Browse within: prompt-engineering 124context-engineering 67Multi-Agent 65github-copilot 52Autonomous Agents 48academic-writing 45ai-assistant 45opencode 45typescript 45code 43literature-review 43agentic-coding 42agent-orchestration 37ai-research 36

architect

01

affaan-m/ECC

Agent

Software architecture specialist for system design, scalability, and technical decision-making. Use PROACTIVELY when planning new features, refactoring large systems, or making architectural decisions.

245k +403 yesterday A 36 tokens original MIT

chief-of-staff

02

affaan-m/ECC

Agent

Personal communication chief of staff that triages email, Slack, LINE, and Messenger. Classifies messages into 4 tiers (skip/infoonly/meetinginfo/actionrequired), generates draft replies, and enforces post-send follow-through via hooks. Use when managing multi-channel communication workflows.

245k +403 yesterday A 61 tokens original MIT

prompt-manager

03

f/prompts.chat

Agent

Agent for managing AI prompts on prompts.chat - search, save, improve, and organize your prompt library.

168k +145 yesterday A 24 tokens

skill-manager

04

f/prompts.chat

Agent

Agent for managing AI Agent Skills on prompts.chat - search, create, and manage multi-file skills for Claude Code.

168k +145 yesterday A 26 tokens

cavecrew-builder

05

JuliusBrussee/caveman

Agent

Surgical 1-2 file edit. Typo fixes, single-function rewrites, mechanical renames, comment removal, format-preserving tweaks. Hard refuses 3+ file scope. Returns caveman diff receipt. Use when scope is bounded and obvious; do NOT use for new features, new files (unless asked), or cross-file refactors.

102k 2d ago A 76 tokens

JuliusBrussee/caveman

Agent

Read-only code locator. Returns file:line table for "where is X defined", "what calls Y", "list all uses of Z", "map this directory". Output is caveman-compressed so the main thread eats 60% fewer tokens than vanilla Explore. Refuses to suggest fixes.

102k 2d ago A 66 tokens

cavecrew-reviewer

07

JuliusBrussee/caveman

Agent

Diff/branch/file reviewer. One line per finding, severity-tagged, no praise, no scope creep. Output format path:line: : . . Use for "review this PR", "review my diff", "audit this file". Skips formatting nits unless they change meaning.

102k 2d ago A 75 tokens

Egonex-AI/Understand-Anything

Agent

Analyzes a codebase's file structure, summaries, and import relationships to identify logical architectural layers and assign every file to exactly one layer.

81k +76 6d ago A 33 tokens original MIT

file-analyzer

09

Egonex-AI/Understand-Anything

Agent

Analyzes batches of source files to produce knowledge graph nodes and edges. Extracts file structure, functions, classes, and relationships using a two-phase approach: structural extraction script followed by LLM semantic analysis.

81k +76 6d ago A 47 tokens original MIT

project-scanner

10

Egonex-AI/Understand-Anything

Agent

Scans a codebase directory to produce a structured inventory of all project files, detected languages, frameworks, import maps, and estimated complexity.

81k +76 6d ago A 33 tokens original MIT

comparator

11

bytedance/deer-flow

Agent

Compare two outputs WITHOUT knowing which skill produced them.

81k yesterday A 0 tokens original MIT

securityengineer

12

paperclipai/paperclip

Agent

Use this template when hiring security engineers who own security posture: threat-model systems, review auth/crypto/input handling, triage supply-chain and LLM-agent risk, and drive concrete remediations.

80k yesterday A 0 tokens original MIT

agents-directory

14

code-yeongyu/oh-my-openagent

Agent

Developer reference for all 11 Oh My OpenAgent agent definitions, factory patterns, tool restrictions, and model routing.

69k +28 today A 26 tokens

docs-researcher

15

upstash/context7

Agent

Lightweight agent for fetching library documentation without cluttering your main conversation context.

61k +26 today A 20 tokens original MIT

agentic-workflows

16

TryGhost/Ghost

Agent

GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.

55k +8 today A 24 tokens original MIT

modules

17

run-llama/llama_index

Agent

These guide provide an overview of how to use our agent classes.

52k 2d ago A 0 tokens original MIT

tools

18

run-llama/llama_index

Agent

Having proper tool abstractions is at the core of building agentic systems in LlamaIndex. Defining a set of Tools is similar to defining any API interface, with the exception that these Tools are meant for agent rather than human use. We allow users to define both a Tool as well as a ToolSpec containing a series of…

52k 2d ago A 0 tokens original MIT

agentic-workflows

19

moeru-ai/airi

Agent

GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.

49k 2d ago A 24 tokens original MIT