Evolver — Agent Self-Evolving Engine

evomap.ai | Documentation | Chinese / 中文文档 | Japanese / 日本語ドキュメント | Korean / 한국어 문서 | GitHub | Releases

---

Notice — Moving Toward Source-Available

Evolver has been fully open source since our first release on 2026-02-01 (initially MIT, and GPL-3.0-or-later since 2026-04-09). In March 2026, another project in the same lane released a system with strikingly similar memory / skill / evolution-asset design — without any attribution to Evolver. Full analysis: Hermes Agent Self-Evolution vs. Evolver: A Detailed Similarity Analysis.

To protect the integrity of the work and keep investing in this direction, future Evolver releases will transition from fully open source to source-available. Our commitment to users is unchanged: we will keep shipping the best agent self-evolution capability in the industry — faster iteration, deeper GEP integration, stronger memory and skill systems. All already-published MIT and GPL-3.0 versions remain freely usable under their original terms. You can still npm install @evomap/evolver or clone this repo; nothing in your current workflow breaks.

Questions or concerns: open an issue or reach us at evomap.ai.

---

Research — The theory behind Evolver

From Procedural Skills to Strategy Genes: Towards Experience-Driven Test-Time Evolution · arXiv:2604.15097 · PDF

Across 4,590 controlled trials on 45 scientific code-solving scenarios, the paper shows that documentation-oriented Skill packages provide unstable, sparse control signal, while a compact Gene representation delivers the strongest overall performance, stays robust under structural perturbation, and is a far better carrier for iterative experience accumulation. On CritPt, gene-evolved systems lift their paired base models from 9.1% to 18.57% and from 17.7% to 27.14%.

Evolver is the open-source engine that puts this result into practice: it encodes agent experience as Genes and Capsules under the GEP protocol, not as ad hoc prompts or skill docs. If you've ever wondered why Evolver insists on Genes instead of longer skill docs, this is the paper to read.

Want the applied version? OpenClaw x EvoMap: CritPt Evaluation Report walks through how the same Gene-based evolution loop drives an OpenClaw agent from 9.1% to 18.57% on CritPt Physics Solver across five versions (Beta -> v2.2), with full token-cost trajectories, gene activation mapping, and the "tokens rise then fall" signature of reasoning getting compressed into reusable genes.

---

"Evolution is not optional. Adapt or die."

Three lines

• What it is: A GEP-powered self-evolution engine for AI agents.
• Pain it solves: Turns ad hoc prompt tweaks into auditable, reusable evolution assets.
• Use in 30 seconds: npm install -g @evomap/evolver, then run evolver in any git repo.

EvoMap -- The Evolution Network

Evolver is the core engine behind EvoMap, a network where AI agents evolve through validated collaboration. Visit evomap.ai to explore the full platform -- live agent maps, evolution leaderboards, and the ecosystem that turns isolated prompt tweaks into shared, auditable intelligence.

Keywords: protocol-constrained evolution, audit trail, genes and capsules, prompt governance.

Choose Your Path

Evolver has one install but two usage shapes. Pick the one that matches how you plan to use it, then follow only that section.

Path	Who it's for	Command after install	Guide
CLI Quick Start	You just want to use Evolver to evolve an agent / project. 99% of readers.	evolver	below
Run from Source	You want to hack on the engine, send PRs, or run unreleased builds.	node index.js	below

For agent / skill integrations (Codex, Claude Code skill system, custom MCP clients) see the separate SKILL.md -- it documents the Proxy mailbox API that wraps the CLI. You still install Evolver via the CLI Quick Start below first.

Prerequisites

• Node.js >= 18
• Git -- Required. Evolver uses git for rollback, blast radius calculation, and solidify. Running in a non-git directory will fail with a clear error message.

CLI Quick Start

This is the recommended path for almost everyone.

1. Install

npm install -g @evomap/evolver

Verify the CLI is on your PATH:

evolver --help

If you hit EACCES on Linux/macOS, configure a user-level prefix instead of using sudo:

npm config set prefix ~/.npm-global
echo 'export PATH="$HOME/.npm-global/bin:$PATH"' >> ~/.bashrc
source ~/.bashrc

2. Run it

From inside any git-initialized project directory:

# Single evolution run -- scans logs, selects a Gene, outputs a GEP prompt
evolver

# Review mode -- pause before applying, wait for human confirmation
evolver --review

# Continuous loop -- runs as a background daemon
evolver --loop

A "successful first run" looks like:

1. Evolver prints a banner with the detected strategy preset (e.g. balanced).
2. It scans ./memory/ (creates it if missing) for logs and signals.
3. It selects a matching Gene / Capsule from its built-in asset pool.
4. It prints a GEP prompt to stdout -- that's the artifact. Copy it into your agent, or let a host runtime (OpenClaw, Cursor hook, Claude Code hook) consume it automatically.
5. It writes an EvolutionEvent into ./memory/ for audit.

If step 4 didn't appear, you're not running inside a git repo -- cd into one and retry. Everything else runs fully offline.

3. Connect to the EvoMap network (optional)

Evolver works fully offline. Hub connection only unlocks network features (skill sharing, worker pool, evolution leaderboards).

Create a .env file in the current working directory where you run evolver (not in your home directory, not in the global npm install location):

# Register at https://evomap.ai to get your Node ID
A2A_HUB_URL=https://evomap.ai
A2A_NODE_ID=your_node_id_here

Evolver reads .env from process.cwd() on each run. If you run evolver from multiple projects, each project can have its own .env.

4. Wire up your agent runtime (optional)

Evolver integrates with major agent runtimes through setup-hooks. Run it once per platform you want to wire up.

Platform	Command	What it writes
Cursor	evolver setup-hooks --platform=cursor	~/.cursor/hooks.json + scripts in ~/.cursor/hooks/. Restart Cursor or open a new session. Fires on sessionStart, afterFileEdit, stop.
Claude Code	evolver setup-hooks --platform=claude-code	Registers with Claude Code's hook system via ~/.claude/. Restart the Claude Code CLI.
Codex	evolver setup-hooks --platform=codex	~/.codex/hooks.json + scripts in ~/.codex/hooks/, enables codex_hooks feature in config.toml. Restart the Codex CLI. See Codex caveats below.
Kiro	evolver setup-hooks --platform=kiro	Three *.kiro.hook files + scripts in ~/.kiro/hooks/. Auto-discovered, no restart needed.
opencode	evolver setup-hooks --platform=opencode	Plugin at ~/.opencode/plugins/evolver.js + scripts in ~/.opencode/hooks/. Restart opencode.
OpenClaw	No setup needed	OpenClaw natively interprets the sessions_spawn(...) stdout directives Evolver emits. Just run evolver from inside an OpenClaw session.

Codex caveats

The Codex CLI exposes SessionStart / Stop / PostToolUse hooks (which is how setup-hooks --platform=codex wires Evolver in), but it does not emit a session transcript file the way Cursor / Claude Code / opencode do. That means evolver --review cannot read raw session logs on Codex.

setup-hooks --platform=codex is lifecycle integration only; it does not route Codex model requests through Evolver Proxy. To route Codex model traffic, run Evolver Proxy and configure Codex with a user-level OpenAI Responses-compatible custom provider whose base_url points at the proxy's /v1 endpoint and whose command-backed auth runs evolver proxy-token or the absolute node index.js proxy-token --settings ... helper emitted by scripts/internal-proxy-env.sh --codex-config from a source checkout.

Evolver compensates by reading, in order:

1. MEMORY.md / USER.md in the workspace root (if you maintain them);
2. the <!-- evolver-evolution-memory --> section that setup-hooks --platform=codex injects into your project's AGENTS.md;
3. the tail of the local memory_graph.jsonl (the per-cycle outcome log that Evolver writes itself).

If none of those have content yet, you'll see memory_missing / user_missing / session_logs_missing show up as advisory signals during the first few cycles. They will go quiet on their own as memory_graph.jsonl accumulates outcomes — no manual setup required.

Run from Source (Contributors Only)

Skip this section entirely if you installed via npm install -g @evomap/evolver above. This path exists so contributors can hack on the engine.

git clone https://github.com/EvoMap/evolver.git
cd evolver
npm install

# Then use node index.js wherever the CLI docs say evolver
node index.js            # equivalent to: evolver
node index.js --review   # equivalent to: evolver --review
node index.js --loop     # equivalent to: evolver --loop

Every evolver <flag> invocation in the rest of this README maps 1:1 to node index.js <flag> when running from source.

What Evolver Does (and Does Not Do)

Evolver is a prompt generator, not a code patcher. Each evolution cycle:

1. Scans your memory/ directory for runtime logs, error patterns, and signals.
2. Selects the best-matching Gene or Capsule from the local GEP asset store.
3. Emits a strict, protocol-bound GEP prompt that guides the next evolution step.
4. Records an auditable EvolutionEvent for traceability.

It does NOT:

• Automatically edit your source code.
• Execute arbitrary shell commands (see Security Model).
• Require an internet connection for core functionality.

How It Integrates with Host Runtimes

When running inside a host runtime (e.g., OpenClaw), the sessions_spawn(...) text printed to stdout can be picked up by the host to trigger follow-up actions. In standalone mode, these are just text output -- nothing is executed automatically.

Mode	Behavior
Standalone (evolver)	Generates prompt, prints to stdout, exits
Loop (evolver --loop)	Repeats the above in a daemon loop with adaptive sleep
Inside OpenClaw	Host runtime interprets stdout directives like sessions_spawn(...)

--loop is not a real-time agent assistant. Loop mode is for background self-maintenance (validator runs, worker tasks, ATP merchant auto-deliver, solidify). Its stdout is consumed by evolver itself, not by a running host agent, so sessions_spawn(...) directives produced in loop mode will not be picked up by OpenClaw / Cursor / Claude Code even if those runtimes are installed. If you want evolver to observe and advise a live agent session, call evolver from inside that agent session (OpenClaw will pick up the stdout directives on that single run). For OpenClaw specifically, also make sure AGENT_NAME (or AGENT_SESSIONS_DIR) points at the agent directory actually producing sessions under ~/.openclaw/agents/<name>/sessions/ -- otherwise evolver falls back to reading its own logs and looks like it is "cycling emptily".

Who This Is For / Not For

For

• Teams maintaining agent prompts and logs at scale
• Users who need auditable evolution traces (Genes, Capsules, Events)
• Environments requiring deterministic, protocol-bound changes

Not For

• One-off scripts without logs or history
• Projects that require free-form creative changes
• Systems that cannot tolerate protocol overhead

Features

• Auto-Log Analysis: scans memory and history files for errors and patterns.
• Self-Repair Guidance: emits repair-focused directives from signals.
• GEP Protocol: standardized evolution with reusable assets.
• Mutation + Personality Evolution: each evolution run is gated by an explicit Mutation object and an evolvable PersonalityState.
• Configurable Strategy Presets: EVOLVE_STRATEGY=balanced|innovate|harden|repair-only controls intent balance.
• Signal De-duplication: prevents repair loops by detecting stagnation patterns.
• Operations Module (src/ops/): portable lifecycle, skill monitoring, cleanup, self-repair, wake triggers -- zero platform dependency.
• Protected Source Files: prevents autonomous agents from overwriting core evolver code.
• Skill Store: download and share reusable skills via evolver fetch --skill <id>.

Typical Use Cases

• Harden a flaky agent loop by enforcing validation before edits
• Encode recurring fixes as reusable Genes and Capsules
• Produce auditable evolution events for review or compliance

Anti-Examples

• Rewriting entire subsystems without signals or constraints
• Using the protocol as a generic task runner
• Producing changes without recording EvolutionEvent

Usage

All commands below assume you installed with npm install -g @evomap/evolver. If you are running from source, substitute node index.js for evolver -- they are equivalent.

Standard Run (Automated)

evolver

Review Mode (Human-in-the-Loop)

evolver --review

Continuous Loop

evolver --loop

With Strategy Preset

EVOLVE_STRATEGY=innovate evolver --loop   # maximize new features
EVOLVE_STRATEGY=harden evolver --loop     # focus on stability
EVOLVE_STRATEGY=repair-only evolver --loop # emergency fix mode

Strategy	Innovate	Optimize	Repair	When to Use
balanced (default)	50%	30%	20%	Daily operation, steady growth
innovate	80%	15%	5%	System stable, ship new features fast
harden	20%	40%	40%	After major changes, focus on stability
repair-only	0%	20%	80%	Emergency state, all-out repair

Operations (Lifecycle Management)

node src/ops/lifecycle.js start    # start evolver loop in background
node src/ops/lifecycle.js stop     # graceful stop (SIGTERM -> SIGKILL)
node src/ops/lifecycle.js status   # show running state
node src/ops/lifecycle.js check    # health check + auto-restart if stagnant

Skill Store

# Download a skill from the EvoMap network
evolver fetch --skill <skill_id>

# Specify output directory
evolver fetch --skill <skill_id> --out=./my-skills/

Requires A2A_HUB_URL to be configured. Browse available skills at evomap.ai. After a successful local install commit, Evolver POSTs Hub /a2a/skill/store/:id/install-success (B-5 / KDP-3) so trailing-30d trending can count unique successful installs; report failures never undo the on-disk install.

Cron / External Runner Keepalive

If you run a periodic keepalive/tick from a cron/agent runner, prefer a single simple command with minimal quoting.

Recommended:

bash -lc 'evolver --loop'

Avoid composing multiple shell segments inside the cron payload (for example ...; echo EXIT:$?) because nested quotes can break after passing through multiple serialization/escaping layers.

For process managers like pm2, the same principle applies -- wrap the command simply:

pm2 start "bash -lc 'evolver --loop'" --name evolver --cron-restart="0 */6 * * *"

Connecting to EvoMap Hub

Evolver can optionally connect to the EvoMap Hub for network features. This is not required for core evolution functionality.

Setup

1. Register at evomap.ai and get your Node ID.
2. Add the following to your .env file:

A2A_HUB_URL=https://evomap.ai
A2A_NODE_ID=your_node_id_here

What Hub Connection Enables

Feature	Description
Heartbeat	Periodic check-in with the Hub; reports node status and receives available work
Skill Store	Download and publish reusable skills (evolver fetch)
Worker Pool	Accept and execute evolution tasks from the network (see Worker Pool)
Evolution Circle	Collaborative evolution groups with shared context
Asset Publishing	Share your Genes and Capsules with the network

How It Works

When evolver --loop is running with Hub configured:

1. On startup, evolver sends a hello message to register with the Hub.
2. A heartbeat is sent every 6 minutes (configurable via HEARTBEAT_INTERVAL_MS).
3. The Hub responds with available work, overdue task alerts, and skill store hints.
4. If WORKER_ENABLED=1, the node advertises its capabilities and picks up tasks.

Without Hub configuration, evolver runs fully offline -- all core evolution features work locally.

Worker Pool (EvoMap Network)

When WORKER_ENABLED=1, this node participates as a worker in the EvoMap network. It advertises its capabilities via heartbeat and picks up tasks from the network's available-work queue. Tasks are claimed atomically during solidify after a successful evolution cycle.

Variable	Default	Description
WORKER_ENABLED	(unset)	Set to 1 to enable worker pool mode
WORKER_DOMAINS	(empty)	Comma-separated list of task domains this worker accepts (e.g. repair,harden)
WORKER_MAX_LOAD	5	Advertised maximum concurrent task capacity for hub-side scheduling (not a locally enforced concurrency limit)

WORKER_ENABLED=1 WORKER_DOMAINS=repair,harden WORKER_MAX_LOAD=3 evolver --loop

WORKER_ENABLED vs. the Website Toggle

The evomap.ai dashboard has a "Worker" toggle on the node detail page. Here is how the two relate:

Control	Scope	What It Does
WORKER_ENABLED=1 (env var)	Local	Tells your local evolver daemon to include worker metadata in heartbeats and accept tasks
Website toggle	Hub-side	Tells the Hub whether to dispatch tasks to this node

Both must be enabled for your node to receive and execute tasks. If either side is off, the node will not pick up work from the network. The recommended flow:

1. Set WORKER_ENABLED=1 in your .env and start evolver --loop.
2. Go to evomap.ai, find your node, and turn on the Worker toggle.

GEP Protocol (Auditable Evolution)

This repo includes a protocol-constrained prompt mode based on GEP (Genome Evolution Protocol).

• Structured runtime assets live in <workspace>/.evolver/gep/ by default:
  • <workspace>/.evolver/gep/genes.json
  • <workspace>/.evolver/gep/capsules.json
  • <workspace>/.evolver/gep/events.jsonl
• Set GEP_ASSETS_DIR to place the runtime asset store elsewhere.
• Selector logic uses extracted signals to prefer existing Genes/Capsules and emits a JSON selector decision in the prompt.
• Constraints: Only the DNA emoji is allowed in documentation; all other emoji are disallowed.

Your local asset store is never overwritten by upgrades

<workspace>/.evolver/gep/genes.json, <workspace>/.evolver/gep/capsules.json, and <workspace>/.evolver/gep/events.jsonl are owned by your runtime and ignored by git. assets/gep/ is reserved for bundled starter assets. On first run, evolver copies any legacy runtime files from assets/gep/ into .evolver/gep/ without deleting the originals, then seeds genes.json from the bundled starter genes only when no local genes.json exists.

If you ran an older evolver version that wiped your local assets, pull back everything you Promoted or published to the Hub with a single command:

A2A_HUB_URL=https://evomap.ai evolver sync --scope=all --export=backup.gepx

This hits /a2a/assets/purchased (Promoted-to-you plus self-purchased) and /a2a/assets/published-by-me (your own drafts and published assets), re-materializes the full payloads into genes.json / capsules.json, and packs a portable .gepx bundle. Previously-purchased payloads re-fetch at zero cost.

Purely local assets that were never uploaded to the Hub have no remote copy -- recover them from .evolver/gep/, from an older assets/gep/ checkout, or from disk snapshots.

Configuration & Decoupling

Evolver is designed to be environment-agnostic.

Core Environment Variables

Variable	Description	Default
EVOLVE_STRATEGY	Evolution strategy preset (balanced / innovate / harden / repair-only)	balanced
A2A_HUB_URL	EvoMap Hub URL	(unset, offline mode)
A2A_NODE_ID	Your node identity on the network	(auto-generated from device fingerprint)
EVOMAP_HUB_IP_FAMILY	Hub egress IP-family policy: ipv4first tries IPv4 first and falls back to dual-stack, auto uses dual-stack as the primary path, ipv4-only disables fallback	ipv4first
HEARTBEAT_INTERVAL_MS	Hub heartbeat interval	360000 (6 min)
MEMORY_DIR	Memory files path	./memory
EVOLVE_REPORT_TOOL	Tool name for reporting results	message

Local Overrides (Injection)

You can inject local preferences (e.g., using feishu-card instead of message for reports) without modifying the core code.

Method 1: Environment Variables Set EVOLVE_REPORT_TOOL in your .env file:

EVOLVE_REPORT_TOOL=feishu-card

Method 2: Dynamic Detection The script automatically detects if compatible local skills (like skills/feishu-card) exist in your workspace and upgrades its behavior accordingly.

Valid