Pithelo

Five agent repos gaining momentum. Every one measured.

Ranked by stars gained over the last 7 days, growth rate and recent commit activity.

Rank 1

google/elephant-goldfish-model

Elephant-Goldfish Model (EGM) is an open-source plugin of skills for Antigravity, Claude Code, and Codex that splits software design into a context-rich 'elephant' agent that brainstorms and drafts specifications, and context-free 'goldfish' subagents that review them. A human resolves trade-offs and approves the design before implementation.

Developers building agent workflows who want a concrete pattern for spec drafting and review using fresh-context subagents (it stops the review if the host agent cannot create them) should look at it.

  • ★ 11,374
  • +★ 7,833 in 7 days
  • 221.2% growth
  • Apache-2.0
  • README ≈ 3,208 tokens to load into context

AI-written summary

Score93.7
Rank 2

DenisSergeevitch/ex-ussr-kinship-research

Evidence-first genealogy skill for AI agents (Codex, Claude Code): church books, civil, military, deportation and repression records across the former USSR. Replies in your language.

  • ★ 1,795
  • +★ 727 in 7 days
  • 68.1% growth
  • MIT
  • README ≈ 4,958 tokens to load into context

AI-written summary

Score91.6
Rank 3

langgenius/dify

Dify is an open-source LLM app development platform that combines AI workflows, RAG pipelines, agent capabilities, model management, and observability integrations (Opik, Langfuse, Arize Phoenix) in one interface. It can be deployed on Dify Cloud, in a VPC, or self-hosted.

Developers building agent or RAG applications who want a single workspace for prototyping and production deployment, with a self-hosting option, may want to evaluate it.

  • ★ 160,364
  • +★ 609 in 7 days
  • 0.4% growth
  • No licence declared
  • README ≈ 5,126 tokens to load into context

AI-written summary

Score75.8
Rank 4

infiniflow/ragflow

RAGFlow is an open-source Retrieval-Augmented Generation engine that combines RAG with agent capabilities to supply context to LLMs. It provides a RAG workflow with a context engine, pre-built agent templates, and data ingestion from sources such as sitemaps and Google BigQuery.

Developers building production RAG or agentic RAG systems over complex or unstructured documents, with either cloud or local deployment, may want to evaluate it.

  • ★ 93,459
  • +★ 475 in 7 days
  • 0.5% growth
  • Apache-2.0
  • README ≈ 7,054 tokens to load into context

AI-written summary

Score75.3
Rank 5

bytedance/deer-flow

DeerFlow 2.0 is an open-source "super agent harness" from ByteDance that orchestrates sub-agents, memory, sandboxes, tools, and extensible skills to handle research, coding, and content-creation tasks lasting minutes to hours. It also includes a message gateway/IM channels, MCP server support, and tracing integrations, and is a ground-up rewrite that shares no code with v1.

Developers building long-running, multi-step agents who want a ready-made harness (sandboxing, memory, sub-agents, skills) rather than assembling those pieces themselves should look at it.

  • ★ 84,963
  • +★ 449 in 7 days
  • 0.5% growth
  • MIT

AI-written summary

Score73.2