FollowAgents AI AGENTS DIRECTORY
FollowAgents Trending

What changed in AI agents this week

Verifiable changes across the agents in our catalog over the last 7 days: stable GitHub releases, star growth and newly added projects. Every item comes from stored source data and links to it — no rewritten news, no blended "heat score".

Data as of 2026-10-19Updated daily. Trend signals never change any agent's FARS score.

New releases this week

Cataloged agents that shipped a stable release (pre-releases excluded) in the last 7 days. Release data has been collected daily from GitHub Releases since 2026-10-19.

  1. Qwen Code

    A multi-provider AI coding agent that runs in your terminal.

    sdk-typescript-v0.1.21 ↗ · 5 stable releases this week
  2. Ouroboros Agent OS

    A specification-first runtime that turns AI coding requests into replayable, verified workflows.

    v0.59.0 ↗ · 11 stable releases this week
  3. Mnemo Cortex

    A local-first cognitive coprocessor for AI agents: active memory, semantic recall, and cross-agent sharing with no cloud.

    v4.27.0 ↗
  4. Node9

    Intercept, audit, and govern risky actions performed by autonomous coding agents.

    v2.34.0 ↗ · 9 stable releases this week
  5. Paseo

    One interface to orchestrate multiple coding agents (Claude Code, Codex, Copilot, OpenCode, Pi) from desktop and mobile.

    v0.12.0 ↗ · 3 stable releases this week
  6. QuantDinger AI Trading OS

    Turn AI-assisted market research into Python strategies, backtests, paper trading, live execution, and monitoring.

    v5.6.4 ↗ · 5 stable releases this week
  7. HarnessRouter Community Edition

    One API to run Codex, Claude Code, Hermes, DeepSeek Harness, and more, self-hosted on your own infrastructure—no harness-specific backends required.

    v0.35.7 ↗ · 12 stable releases this week
  8. Hive Agent Harness

    A production runtime for multi-agent business workflows with graph execution, recovery, observability, and human oversight.

    v1.0.10 ↗ · 11 stable releases this week
  9. Okou

    Delegate cross-app work in natural language while keeping permissions, approvals, and execution under team control.

    sandbox-mock-v0.17.3 ↗ · 20 stable releases this week
  10. Loki Mode

    Turns software specs into tested code with independently checkable completion evidence.

    v11.17.78 ↗ · 20 stable releases this week
  11. MaiSaka

    A human-style LLM companion designed for ongoing QQ group conversations.

    v1.3.10 ↗ · 4 stable releases this week
  12. Hermes Studio

    A self-hosted workspace for running Hermes Agent chats, workflows, channels, and local runtime operations.

    v0.7.37 ↗ · 6 stable releases this week
  13. Orca

    A desktop ADE for running and reviewing parallel CLI coding agents in isolated Git worktrees.

    v1.4.230 ↗ · 3 stable releases this week
  14. CC Safety Net — Safety Net for AI Coding Agents

    Intercept and block destructive git and filesystem commands, and secret file access, before AI coding agents execute them.

    v2.6.15 ↗ · 6 stable releases this week
  15. OpenCode Goal Plugin

    Adds Codex-style long-running goal mode to OpenCode so AI coding agents keep working toward one explicit objective until complete, blocked, or cleared.

    v0.1.66 ↗ · 6 stable releases this week
  16. GenericAgent

    A local autonomous-agent framework that turns completed work into reusable skills.

    v0.2.1 ↗
  17. PageIndex: Vectorless, Reasoning-based RAG

    Build hierarchical tree indexes and reason over them for context-aware retrieval - no vector DB, no chunking.

    v0.4.4 ↗ · 5 stable releases this week
  18. Chat On Steroids

    Connect ChatGPT to local projects, terminals, and durable multi-worker development workflows.

    v2.1.42 ↗ · 8 stable releases this week
  19. PowerContext

    Not only memory but a full story: keep context with your work so humans and agents can hand off and pick up where things left off.

    powercontext-v1.4.0 ↗
  20. Keploy API Testing & Mock Platform

    Auto-generate API tests and mocks from real user traffic with zero code changes — faster than unit tests.

    v3.6.144 ↗ · 20 stable releases this week

GitHub star growth

Ranked by net stars gained per day over the window actually covered (at least 3 days). Stars are not users, downloads or quality.

  1. REA: Reverse Engineer Anything with Agents

    Hands reverse engineering to your coding agent, from app behavior down to native binaries.

    +25302.1 / day 7-day window · 327k stars
  2. AI Job Search

    The job search that runs on your machine. AI job application framework built on Claude Code: evaluate postings, tailor CVs, write cover letters, prep interviews.

    +1160.1 / day 7-day window · 54k stars
  3. Orca

    A desktop ADE for running and reviewing parallel CLI coding agents in isolated Git worktrees.

    +946.6 / day 7-day window · 97k stars
  4. ECC Engineering Harness

    A cross-harness engineering workflow system for planning, testing, review, memory, and agent-configuration security.

    +813.0 / day 7-day window · 283k stars
  5. iFixAi Agent Auditor

    Audit AI-agent governance failures and operational risks in about 120 seconds.

    +799.9 / day 7-day window · 30k stars
  6. Ponytail

    Guides coding agents to reuse what already exists and write the smallest implementation that preserves safety boundaries.

    +785.6 / day 7-day window · 167k stars
  7. DeepSeek Harness (dsh)

    An open-source agent harness from DeepSeek AI where everything is a plugin.

    +785.3 / day 7-day window · 254k stars
  8. PentAGI

    A self-hosted, multi-agent platform for authorized penetration-testing workflows in isolated containers.

    +649.4 / day 7-day window · 31k stars
  9. Scientific Agent Skills

    Turn any AI agent into an AI Scientist: 159 ready-to-use skills and 100+ scientific databases covering biology, chemistry, medicine, and drug discovery.

    +597.3 / day 7-day window · 53k stars
  10. opencode

    The open source coding agent for your terminal

    +572.1 / day 7-day window · 217k stars
  11. Taste-Skill: AI Frontend Aesthetic Upgrade

    Give your AI good taste — stop generic, boring frontend code and produce premium, design-conscious UIs.

    +559.7 / day 7-day window · 99k stars
  12. Context Mode — Context Optimization for AI Coding Agents

    Cut context window bloat, persist session memory, and enforce tool routing across 17 platforms via MCP and hooks.

    +533.9 / day 7-day window · 31k stars
  13. AI Engineering from Scratch

    A free, open-source curriculum of 503 lessons across 20 phases, teaching you to build AI end-to-end from math to agents.

    +449.6 / day 7-day window · 71k stars
  14. Agent Skills — Production-Grade Engineering Skills for AI Agents

    Structured workflows, quality gates, and senior-engineer practices for AI coding agents across the full development lifecycle.

    +396.3 / day 7-day window · 108k stars
  15. Graphify – Turn Any Codebase into a Queryable Knowledge Graph

    Turn code, docs, SQL schemas, and PDFs into a queryable knowledge graph with /graphify in your AI coding assistant – no vector store needed.

    +395.1 / day 7-day window · 129k stars

Newly added

Agents whose profile was published in the last 7 days.

  1. MADDPG in PyTorch

    A PyTorch reference implementation of Multi-Agent Deep Deterministic Policy Gradients (MADDPG).

  2. Lemon Persistent Coding Agent

    Keep coding work running in a self-hosted Elixir/OTP daemon, and resume it from a terminal, browser, or phone.

  3. NeuroSquad Terminal Dashboard

    Run and manage several AI coding CLIs from one terminal dashboard.

  4. Station Research Environment

    Coordinate autonomous agents in a shared research environment to run scored experiments and build a scientific record.

  5. rpi: Rust Coding-Agent Runtime

    Build, run, and extend coding agents with an embeddable Rust runtime and a terminal CLI.

  6. apowerb Agent Platform

    Build self-hosted production agents that connect business systems, knowledge bases, and unattended triggers.

  7. AI Switcher

    Manage and switch named accounts for local AI coding tools from one command.

  8. AgentEvals Trace Evaluation

    Evaluate AI agent behavior from existing OpenTelemetry traces without rerunning the agent.

  9. Eleven Reverse Engineering Workbench

    Bring ACP agents into a desktop workbench to inspect, annotate, and patch binaries.

  10. ESP-Claw Edge Agent Framework

    Define device behavior through chat and run sensing, decisions, and actions on Espressif chips.

  11. ESP32 iPhone Operator

    Automate a real iPhone with an ESP32-S3 and a vision model, without a computer at runtime.

  12. kagent Website & Docs

    The official website and documentation source for kagent and kMCP, covering the Kubernetes-native agent framework and its adopters.

  13. Mycelium

    Four questions before the first source file, so you and your coding agent don't spend the weekend building the wrong thing.

  14. Kubeflow Docs Agent

    The official RAG-based documentation assistant for the Kubeflow website, with hybrid retrieval, streaming answers and structured citations.

  15. Open Managed Agents (OpenMA)

    Open-source managed agent runtime with durable sessions, execution and recovery — any model, any harness, any sandbox, any cloud.

83 added this week — browse all agents →

Latest guides and topics

Hand-written topic hubs and tutorials with sources and verification notes.

REA explained: AI reverse engineering and where to start

Understand how REA connects your coding agent, MCP and analysis engines, then choose a setup guide, a project review or a related tool for your task.

Updated 2026-10-17

REA setup and first-use guide

Choose a first REA workflow, connect your coding agent, and diagnose missing tools with official documentation and clear checks.

Updated 2026-10-17

REA hands-on: find an Electron CSV export channel

A reproducible REA 6.5.0 static analysis of our Electron source fixture, with a downloadable sample, real bridge and IPC findings, and failures explained.

Updated 2026-10-17