evolving-agents

Multi-agent orchestration toolkit that automatically discovers, creates, and evolves AI agents within governance boundaries using MongoDB-backed persistence.

Evaluated Mar 08, 2026 (0d ago) vlatest (archived)
Homepage ↗ Repo ↗ AI & Machine Learning agents multi-agent orchestration mongodb openai beeai archived
⚙ Agent Friendliness
30
/ 100
Can an agent use this?
🔒 Security
49
/ 100
Is it safe for agents?
⚡ Reliability
21
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
0
Documentation
55
Error Messages
35
Auth Simplicity
55
Rate Limits
25

🔒 Security

TLS Enforcement
70
Auth Strength
55
Scope Granularity
30
Dep. Hygiene
40
Secret Handling
45

MongoDB credentials embedded in connection string. OpenAI key in .env file. No secret rotation or vault integration.

⚡ Reliability

Uptime/SLA
10
Version Stability
20
Breaking Changes
30
Error Recovery
25
AF Security Reliability

Best When

Never - project is archived. Use LLMunix (the successor) instead.

Avoid When

Always - project is officially discontinued and the authors themselves called it over-engineered.

Use Cases

  • Orchestrating multi-agent workflows for complex tasks like invoice processing
  • Semantic component search and agent discovery via MongoDB Vector Search
  • Human-in-the-loop review of agent intent plans
  • Evolving and adapting agents based on execution feedback

Not For

  • Production use (project is archived/sunset as of July 2025)
  • Simple single-agent tasks
  • Teams without MongoDB Atlas infrastructure
  • Anyone wanting a maintained framework (successor is LLMunix)

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
No
SDK
Yes
Webhooks
No

Authentication

Methods: api-key
OAuth: No Scopes: No

Requires OpenAI API key and MongoDB connection string with credentials.

Pricing

Model: free
Free tier: Yes
Requires CC: No

Open source (Apache 2.0). Requires OpenAI API credits and MongoDB Atlas (has free tier).

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • Project is ARCHIVED - no maintenance or updates
  • Requires MongoDB Atlas with Vector Search indexes
  • Complex setup with multiple embedding dimensions to configure
  • Authors describe it as over-engineered

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for evolving-agents.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-03-08.

6961
Packages Evaluated
25669
Need Evaluation
173
Need Re-evaluation
Community Powered