self-evolving agents

214 tagged self-evolving, measured the same way as everything else here.

skill-creator

02

volcengine/OpenViking

Skill Claude CodeCodex

Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.

35k +369 yesterday A 28 tokens AGPL-3.0

openviking-memory

03

volcengine/OpenViking

Plugin Claude Code

Long-term semantic memory for Claude Code, powered by OpenViking. Auto-recall relevant memories at session start and capture important information during conversations.

35k +369 yesterday A tokens not measured AGPL-3.0

ov

04

volcengine/OpenViking

Command

Show OpenViking memory plugin status — server, identity, last injection / recall, toggles.

35k +369 yesterday A 19 tokens AGPL-3.0

SessionStart

05

volcengine/OpenViking

Hook

Runs when a session starts, executing session-start.mjs via node. From volcengine/OpenViking.

35k +369 yesterday A tokens not measured AGPL-3.0

UserPromptSubmit

06

volcengine/OpenViking

Hook

Runs when you submit a prompt, before the agent sees it, executing auto-recall.mjs via node. From volcengine/OpenViking.

35k +369 yesterday A tokens not measured AGPL-3.0

PostToolUse

07

volcengine/OpenViking

Hook

Runs after a tool call finishes for Read tool calls, executing skill-experience.mjs via node. From volcengine/OpenViking.

35k +369 yesterday A tokens not measured AGPL-3.0

llm-wiki

08

volcengine/OpenViking

Skill Claude CodeCodex

Compile heterogeneous knowledge sources—including documents, notes, web content, transcripts, research materials, and code repositories—into a Karpathy-style, evidence-grounded LLM Wiki with a maintained index; default entity and concept pages; and selective method, comparison, analysis, or reason-requested summary…

35k +369 yesterday A 90 tokens AGPL-3.0

volcengine/OpenViking

Skill Claude CodeCodex

Install and configure the OpenViking long-term memory plugin for OpenClaw via natural conversation. Once installed, the plugin automatically captures facts from chats and recalls relevant context before each reply (auto-capture + auto-recall, cross-session). Covers prerequisites, install through OpenClaw's plugin…

35k +369 changed yesterday A 191 tokens AGPL-3.0

zylos-ai/zylos-core

Instructions file

Instructions for zylos-ai/zylos-core, covering claude.md, project standards, programming language, module system and release process.

1.2k 15d ago B 1,517 tokens original MIT

activity-monitor

12

zylos-ai/zylos-core

Skill Claude CodeCodex

Guardian service that monitors the active runtime agent's state and automatically restarts it if stopped. Use when checking agent liveness state or understanding the auto-restart mechanism.

1.2k 15d ago A 36 tokens original MIT

zylos-ai/zylos-core

Skill Claude CodeCodex

Guidelines for managing zylos components via CLI and C4 channels. Use when installing, upgrading, or uninstalling components, or when user asks about available components.

1.2k 15d ago A 37 tokens original MIT

zylos-memory

14

zylos-ai/zylos-core

Skill Claude CodeCodex

Core memory system. Maintains persistent memory across sessions via tiered markdown files following the Inside Out model. Handles Memory Sync (processing conversations into structured memory), session rotation, consolidation, and context-aware state saving. Must be launched via a runtime-appropriate background…

1.2k 15d ago A 68 tokens original MIT

zylos-core

15

zylos-ai/zylos-core

Settings file Claude Code

Agent settings configuring model, autoMemoryEnabled, autoDreamEnabled, statusLine.

1.2k 15d ago A tokens not measured original MIT

a-evolve CLAUDE.md

16

A-EVO-Lab/a-evolve

Instructions file

Claude Code instructions for A-EVO-Lab/a-evolve, covering claude.md, project overview, repository structure, arc-agi-3 key concepts and game environment (arc-agi sdk).

769 +4 11d ago A 1,475 tokens

harness-optimizer

17

A-EVO-Lab/a-evolve

Skill Claude CodeCodex

Optimize an AI agent's harness for MCP-Atlas benchmark. Use when analyzing execution traces, diagnosing failures, and proposing improved prompts, skills, or harness code.

769 +4 11d ago A 37 tokens

A-EVO-Lab/a-evolve

Skill Claude CodeCodex

When to prefer GUI mouse clicks over keyboard shortcuts — especially for formatting, multi-step visual tasks, and cross-application workflows.

769 +4 11d ago A 31 tokens

data-formats

19

A-EVO-Lab/a-evolve

Skill Claude CodeCodex

Reading, writing, and converting common data formats (CSV, Excel, JSON, YAML) with correct handling of encoding, types, and edge cases.

769 +4 11d ago A 34 tokens

git-workflow

20

EXboys/evotown

Cursor rule Cursor

Git workflow — prefer main, avoid extra feature branches.

665 9d ago A 326 tokens

issue-pr-workflow

21

EXboys/evotown

Cursor rule Cursor

Issue-first workflow — open issue before PR, link with Closes.

665 9d ago A 418 tokens

agent-browser

22

EXboys/evotown

Skill Claude CodeCodex

Browser automation CLI for AI agents. Requires Node.js with agent-browser. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a…

665 9d ago A 115 tokens

find-skills

23

EXboys/evotown

Skill Claude CodeCodex

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

665 9d ago A 67 tokens

skill-creator

24

EXboys/evotown

Skill Claude CodeCodex

Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.

665 9d ago A 28 tokens

At most 3 mods per repository are shown here — the rest are on their repository pages: