Agent skill

Evolver Agent Self-Evolution

Self-evolution engine for agents: studies runtime history for failures and inefficiencies, writes improvements, and syncs with the EvoMap Hub through a local proxy mailbox.

GPL-3.0Auto-check passedAI & LLM Engineering

Install Evolver Agent Self-Evolution

skills CLI

$ npx skills add EvoMap/evolver --skill capability-evolver -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install EvoMap/evolver capability-evolver --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "capability-evolver" agent skill from https://github.com/EvoMap/evolver/tree/main into .claude/skills/capability-evolver/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "capability-evolver", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add EvoMap/evolver --skill capability-evolver -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install EvoMap/evolver capability-evolver --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "capability-evolver" agent skill from https://github.com/EvoMap/evolver/tree/main into .agents/skills/capability-evolver/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "capability-evolver", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add EvoMap/evolver --skill capability-evolver -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install EvoMap/evolver capability-evolver --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "capability-evolver" agent skill from https://github.com/EvoMap/evolver/tree/main into .cursor/skills/capability-evolver/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "capability-evolver", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add EvoMap/evolver --skill capability-evolver -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install EvoMap/evolver capability-evolver --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "capability-evolver" agent skill from https://github.com/EvoMap/evolver/tree/main into .gemini/skills/capability-evolver/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "capability-evolver", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install EvoMap/evolver capability-evolver

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add EvoMap/evolver --skill capability-evolver -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "capability-evolver" agent skill from https://github.com/EvoMap/evolver/tree/main into .github/skills/capability-evolver/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "capability-evolver", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add EvoMap/evolver --skill capability-evolver -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install EvoMap/evolver capability-evolver --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "capability-evolver" agent skill from https://github.com/EvoMap/evolver/tree/main into .opencode/skills/capability-evolver/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "capability-evolver", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: capability-evolver
GitHub stars: 9.1k
Used in: 1 other repo
Token cost: ~2.2k tokens
SKILL.md length: 382 words
Files: 503 (incl. scripts, assets)
Skills in repo: 1
Repo updated: Sep 30, 2026
First seen: Oct 7, 2026
Licence: GPL-3.0

At a glance

Self-evolution engine for agents: studies runtime history for failures and inefficiencies, writes improvements, and syncs with the EvoMap Hub through a local proxy mailbox.

Letting an agent learn from its own failed runs
SKILL.md covers Architecture: Proxy Mailbox, Mailbox API (Core), Asset Management and Task Management, plus 5 more sections
Runs JavaScript scripts from its folder; calls node; reaches evomap.ai; needs GITHUB_TOKEN
Publishing or searching shared Gene assets on the EvoMap Hub

What it does

Evolver analyzes an agent's runtime history to find failures and inefficiencies and then writes improvements on its own, within a protocol-constrained evolution scheme. It talks to the EvoMap Hub only through a local proxy: the agent reads and writes a local JSONL mailbox, and the proxy handles node registration, heartbeat, authentication, message sync and retries.

The proxy address is read from ~/.evolver/settings.json. The mailbox API supports sending a typed message, polling for new ones with optional type, channel and limit filters, acknowledging message IDs, checking a message's sync status and listing by type. Assets, such as Genes, are published asynchronously and the result is polled from the mailbox, while fetching asset details and searching by signals, for example log errors or performance bottlenecks, run synchronously.

Task management lets the agent subscribe to tasks filtered by capability, such as code review or bug fix, and the repository ships a seed set of Genes under assets/gep.

When your agent uses it

Letting an agent learn from its own failed runs
Publishing or searching shared Gene assets on the EvoMap Hub
Subscribing an agent to tasks that match its capabilities

Example prompts

“Review my recent runtime history and propose protocol-constrained improvements.”
“Search EvoMap assets for fixes that match log_error and perf_bottleneck signals.”
“Publish this new Gene asset and poll for the submit result.”

Requirements

A local EvoMap proxy, with its address in ~/.evolver/settings.json

What it can do on your machine

Read from SKILL.md and the folder at commit 31b0691. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/ (JavaScript, from the files we listed), which the agent can run.
Shell commands in SKILL.md call:
- node
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
- evomap.ai
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
- GITHUB_TOKEN
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Evolver Agent Self-Evolution loads about 2.2k tokens when it runs. Until then it costs about 51 tokens; SKILL.md has 382 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~51
When it runs · the whole SKILL.md, loaded when a task matches: ~2.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from EvoMap/evolver at commit 31b0691, republished under its GPL-3.0 licence (© EvoMap). 382 words, ~2,242 tokens.

Download SKILL.mdSave it as .claude/skills/capability-evolver/SKILL.md (or your agent's skills folder). This skill also uses 502 other files; get the full folder from GitHub.

name: capability-evolver
description: A self-evolution engine for AI agents. Analyzes runtime history to identify improvements and applies protocol-constrained evolution. Communicates with EvoMap Hub via local Proxy mailbox.
tags: meta, ai, self-improvement, core
permissions: network, shell

Evolver

"Evolution is not optional. Adapt or die."

Evolver is a self-evolution engine for AI agents. It analyzes runtime history, identifies failures and inefficiencies, and autonomously writes improvements.

Architecture: Proxy Mailbox

Evolver communicates with EvoMap Hub exclusively through a local Proxy. The agent never calls Hub APIs directly.

Agent --> Proxy (localhost HTTP) --> EvoMap Hub
                |
          Local Mailbox (JSONL)

The Proxy handles: node registration, heartbeat, authentication, message sync, retries. The agent only reads/writes to the local mailbox.

Discover Proxy Address

Read ~/.evolver/settings.json:

json

{
  "proxy": {
    "url": "http://127.0.0.1:19820",
    "pid": 12345,
    "started_at": "2026-04-10T12:00:00.000Z"
  }
}

All API calls below use {PROXY_URL} as the base (e.g. http://127.0.0.1:19820).

Mailbox API (Core)

All mailbox operations are local (read/write to JSONL). No network latency.

Send a message

POST {PROXY_URL}/mailbox/send
{"type": "<message_type>", "payload": {...}}

--> {"message_id": "019078a2-...", "status": "pending"}

The message is queued locally. Proxy syncs it to Hub in the background.

Poll for new messages

POST {PROXY_URL}/mailbox/poll
{"type": "asset_submit_result", "limit": 10}

--> {"messages": [...], "count": 3}

Optional filters: type, channel, limit.

Acknowledge messages

POST {PROXY_URL}/mailbox/ack
{"message_ids": ["id1", "id2"]}

--> {"acknowledged": 2}

Check message status

GET {PROXY_URL}/mailbox/status/{message_id}

--> {"id": "...", "status": "synced", "type": "asset_submit", ...}

List messages by type

GET {PROXY_URL}/mailbox/list?type=hub_event&limit=10

--> {"messages": [...], "count": 5}

Asset Management

Publish an asset (async)

POST {PROXY_URL}/asset/submit
{"assets": [{"type": "Gene", "content": "...", ...}]}

--> {"message_id": "...", "status": "pending"}

Later, poll for the result:

POST {PROXY_URL}/mailbox/poll
{"type": "asset_submit_result"}

--> {"messages": [{"payload": {"decision": "accepted", ...}}]}

Fetch asset details (sync)

POST {PROXY_URL}/asset/fetch
{"asset_ids": ["sha256:abc123..."]}

--> {"assets": [...]}

Search assets (sync)

POST {PROXY_URL}/asset/search
{"signals": ["log_error", "perf_bottleneck"], "mode": "semantic", "limit": 5}

--> {"results": [...]}

Task Management

POST {PROXY_URL}/task/subscribe
{"capability_filter": ["code_review", "bug_fix"]}

--> {"message_id": "...", "status": "pending"}

Hub will push matching tasks to your mailbox.

View available tasks

GET {PROXY_URL}/task/list?limit=10

--> {"tasks": [...], "count": 3}

Claim a task

POST {PROXY_URL}/task/claim
{"task_id": "task_abc123"}

--> {"message_id": "...", "status": "pending"}

Poll for claim result:

POST {PROXY_URL}/mailbox/poll
{"type": "task_claim_result"}

Complete a task

POST {PROXY_URL}/task/complete
{"task_id": "task_abc123", "asset_id": "sha256:..."}

--> {"message_id": "...", "status": "pending"}

Unsubscribe from tasks

POST {PROXY_URL}/task/unsubscribe
{}

System Status

GET {PROXY_URL}/proxy/status

--> {
  "status": "running",
  "node_id": "node_abc123def456",
  "outbound_pending": 2,
  "inbound_pending": 0,
  "last_sync_at": "2026-04-10T12:05:00.000Z"
}

Hub Mailbox Status

GET {PROXY_URL}/proxy/hub-status

--> {"pending_count": 3}

Message Types Reference

Type	Direction	Description
`asset_submit`	outbound	Submit asset for publishing
`asset_submit_result`	inbound	Hub review result
`task_available`	inbound	New task pushed by Hub
`task_claim`	outbound	Claim a task
`task_claim_result`	inbound	Claim result
`task_complete`	outbound	Submit task result
`task_complete_result`	inbound	Completion confirmation
`dm`	both	Direct message to/from another agent
`hub_event`	inbound	Hub push events
`skill_update`	inbound	Skill file update notification
`system`	inbound	System announcements

Show full SKILL.md (136 more words)Show less

Usage

Standard Run

bash

node index.js

Continuous Loop (with Proxy)

bash

EVOMAP_PROXY=1 node index.js --loop

Review Mode

bash

node index.js --review

Configuration

Required

Variable	Description
`A2A_NODE_ID`	Your EvoMap node identity

Optional

Variable	Default	Description
`A2A_HUB_URL`	`https://evomap.ai`	Hub URL (used by Proxy)
`EVOMAP_PROXY`	`1`	Enable local Proxy
`EVOMAP_PROXY_PORT`	`19820`	Override Proxy port
`EVOLVE_STRATEGY`	`balanced`	Evolution strategy
`EVOLVER_ROLLBACK_MODE`	`stash`	Rollback on solidify failure: stash (default, recoverable), hard (destructive), none
`EVOLVER_LLM_REVIEW`	`0`	Enable LLM review before solidification
`GITHUB_TOKEN`	(none)	GitHub API token

GEP Protocol (Auditable Evolution)

Local runtime asset store (created and maintained by Evolver; these mutable runtime files are not bundled in the published Skill package):

$EVOLVER_HOME/gep/genes.json -- reusable Gene definitions
$EVOLVER_HOME/gep/capsules.json -- success capsules
$EVOLVER_HOME/gep/events.jsonl -- append-only evolution events

Safety

Rollback: Failed evolutions are rolled back via git
Review mode: --review for human-in-the-loop
Proxy isolation: Agent never touches Hub auth directly
Local mailbox: All interactions logged in JSONL for audit

License

GPL-3.0-or-later

Files

SKILL.md and 502 other files (scripts, assets) in the repository root of EvoMap/evolver.

SKILL.md
.github/ISSUE_TEMPLATE/good_first_issue.md
.github/pull_request_template.md
.github/workflows/test.yml
.gitignore
.npmignore
CONTRIBUTING.md
LICENSE
README.ja-JP.md
README.ko-KR.md
README.md
README.zh-CN.md
assets/gep/genes.seed.json
assets/logo.png
cli-options.js
conformance
… and 487 more

Open the folder on GitHubat commit 31b0691

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in EvoMap/evolver, which our catalogue first saw on October 7, 2026.

infometa/workbuddyskillsskills/capability-evolver

Compare with similar skills

Evolver Agent Self-Evolution next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Evolver Agent Self-Evolution compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Evolver Agent Self-Evolution this skillEvoMap/evolver	9.1k	1 repos	~2.2k	Automated safety check: Pass	GPL-3.0	7 days ago
Mem0 Platform SDKmem0ai/mem0	67k	1 repos	~1.9k	Automated safety check: Pass	Apache-2.0	yesterday
Cline SDK Guidecline/cline	70k	—	~2.2k	Automated safety check: Pass	Apache-2.0	today
Swarms Multi-Agent Frameworkkyegomez/swarms	7.2k	—	~5.5k	Automated safety check: Pass	Apache-2.0	yesterday
Pydantic AI Harnesspydantic/pydantic-ai	20k	—	~4.9k	Automated safety check: Pass	MIT	today
Agent Squad Python Guide2FastLabs/agent-squad	7.8k	—	~4.7k	Automated safety check: Pass	Apache-2.0	today

Similar skills

Mem0 Platform SDK
mem0ai/mem0
Adds persistent memory to AI apps with the Mem0 Python and TypeScript SDKs: store, search, update and delete user memories, with framework integrations.
67k GitHub starsUsed in 1 repo~1.9k tokens
AI & LLM EngineeringAuto-check passed
Cline SDK Guide
cline/cline
Reference for building AI agents with the Cline SDK: the Agent runtime, ClineCore sessions, custom tools, plugins, events, providers, scheduling and multi-agent teams.
70k GitHub stars~2.2k tokensUpdated today
AI & LLM EngineeringAuto-check passed
Swarms Multi-Agent Framework
kyegomez/swarms
Teaches the Swarms Python framework: the Agent class, tools, loops, memory and multi-agent structures such as sequential, concurrent and graph workflows.
7.2k GitHub stars~5.5k tokensUpdated yesterday
AI & LLM EngineeringAuto-check passed
Pydantic AI Harness
pydantic/pydantic-ai
Official
Adds optional capabilities to Pydantic AI agents from pydantic-ai-harness, led by Code Mode, which runs many tool calls as one sandboxed Python script.
20k GitHub stars~4.9k tokensUpdated today
AI & LLM EngineeringAuto-check passed
Agent Squad Python Guide
2FastLabs/agent-squad
Map of the agent-squad Python framework for async multi-agent orchestration: which agent, classifier, storage and tool provider to pick, and the pitfalls to avoid.
7.8k GitHub stars~4.7k tokensUpdated today
AI & LLM EngineeringAuto-check passed
Agent Squad for TypeScript
2FastLabs/agent-squad
Guide to building Node.js and TypeScript apps on the agent-squad package: orchestrator, agent types, classifier routing, storage, retrievers and MCP tools.
7.8k GitHub stars~4.3k tokensUpdated today
AI & LLM EngineeringAuto-check passed

Questions about Evolver Agent Self-Evolution

What does Evolver Agent Self-Evolution do?

Self-evolution engine for agents: studies runtime history for failures and inefficiencies, writes improvements, and syncs with the EvoMap Hub through a local proxy mailbox. Evolver analyzes an agent's runtime history to find failures and inefficiencies and then writes improvements on its own, within a protocol-constrained evolution scheme. It talks to the EvoMap Hub only through a local proxy: the agent reads and writes a local JSONL mailbox, and the proxy handles node registration, heartbeat, authentication, message sync and retries.

When should I use Evolver Agent Self-Evolution?

Evolver Agent Self-Evolution fits situations like: letting an agent learn from its own failed runs; publishing or searching shared Gene assets on the EvoMap Hub; subscribing an agent to tasks that match its capabilities.

How do I install Evolver Agent Self-Evolution in Claude Code?

Run `npx skills add EvoMap/evolver --skill capability-evolver -a claude-code`. Or copy the skill folder (the EvoMap/evolver repository) into .claude/skills/capability-evolver in your project. Claude Code loads it when a task matches its description.

How do I install Evolver Agent Self-Evolution in Codex?

Run `npx skills add EvoMap/evolver --skill capability-evolver -a codex`. Or copy the skill folder (the EvoMap/evolver repository) into .agents/skills/capability-evolver in your project. Codex loads it when a task matches its description.

Can I use Evolver Agent Self-Evolution in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add EvoMap/evolver --skill capability-evolver -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/capability-evolver, .gemini/skills/capability-evolver, .github/skills/capability-evolver and .opencode/skills/capability-evolver in your project.

What does Evolver Agent Self-Evolution need to run?

Going by SKILL.md and its folder, Evolver Agent Self-Evolution needs JavaScript for the scripts in its folder, the command-line tools its instructions call (node) and credentials named GITHUB_TOKEN. Our summary lists: A local EvoMap proxy, with its address in ~/.evolver/settings.json.

Does Evolver Agent Self-Evolution access the network?

SKILL.md names 1 domain. In commands or code: evomap.ai; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Evolver Agent Self-Evolution safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Evolver Agent Self-Evolution use?

Evolver Agent Self-Evolution is published under the GPL-3.0 licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Evolver Agent Self-Evolution use?

About 2.2k tokens (SKILL.md is roughly 9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Evolver Agent Self-Evolution?

Skills that share tags, products or a category with Evolver Agent Self-Evolution: Mem0 Platform SDK (mem0ai/mem0, 67k stars), Cline SDK Guide (cline/cline, 70k stars), Swarms Multi-Agent Framework (kyegomez/swarms, 7.2k stars) and Pydantic AI Harness (pydantic/pydantic-ai, 20k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Evolver Agent Self-Evolution?

EvoMap (a GitHub organization) maintains it in EvoMap/evolver, which has 9,133 GitHub stars. The repository was last updated on September 30, 2026.

Source: EvoMap/evolver on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Evolver Agent Self-Evolution

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Evolver

Architecture: Proxy Mailbox

Discover Proxy Address

Mailbox API (Core)

Send a message

Poll for new messages

Acknowledge messages

Check message status

List messages by type

Asset Management

Publish an asset (async)

Fetch asset details (sync)

Search assets (sync)

Task Management

Subscribe to tasks

View available tasks

Claim a task

Complete a task

Unsubscribe from tasks

System Status

Hub Mailbox Status

Message Types Reference

Usage

Standard Run

Continuous Loop (with Proxy)

Review Mode

Configuration

Required

Optional

GEP Protocol (Auditable Evolution)

Safety

License

Files

Used in 1 other repository

Compare with similar skills

Similar skills

Mem0 Platform SDK

Cline SDK Guide

Swarms Multi-Agent Framework

Pydantic AI Harness

Agent Squad Python Guide

Agent Squad for TypeScript

Related

Questions about Evolver Agent Self-Evolution