golemcore-bot

GolemCore Bot is a Java/Spring Boot framework and runnable agent that supports skill-based behaviors (Markdown SKILL.md with YAML frontmatter), MCP-based tool server integrations (stdio), tiered multi-LLM routing, optional memory and RAG, and built-in sandboxed tools (with confirmation for destructive actions). It can run as a CLI/Telgram bot and provides a web dashboard and HTTP triggers (webhooks).

Evaluated Mar 30, 2026 (21d ago)
Homepage ↗ Repo ↗ Ai Ml ai-agent agent-framework mcp tool-use rag skills spring-boot telegram-bot java
⚙ Agent Friendliness
46
/ 100
Can an agent use this?
🔒 Security
42
/ 100
Is it safe for agents?
⚡ Reliability
24
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
45
Documentation
70
Error Messages
0
Auth Simplicity
55
Rate Limits
10

🔒 Security

TLS Enforcement
40
Auth Strength
45
Scope Granularity
20
Dep. Hygiene
50
Secret Handling
55

README indicates sandboxed tool execution and confirmation for destructive actions, plus dashboard password initialization and optional Telegram allowlist. However, there is no explicit evidence here of TLS enforcement policy, robust auth/token design, fine-grained authorization scopes, secret-handling guarantees (beyond suggesting config files/env vars), or dependency/security posture.

⚡ Reliability

Uptime/SLA
0
Version Stability
35
Breaking Changes
30
Error Recovery
30
AF Security Reliability

Best When

You want to self-host a Java agent runtime with MCP tool integration and a skill-based architecture, and you can manage LLM API keys and container deployment.

Avoid When

You require a simple, well-specified external API for programmatic consumption (OpenAPI/SDK/webhooks contracts not evidenced here) or you cannot safely operate sandbox/container tooling.

Use Cases

  • Building autonomous agents with reusable “skills” and pipelines
  • Integrating external tools via MCP tool servers (stdio-based)
  • Routing different workloads to different LLM tiers/models
  • Automating tasks on a schedule (Auto Mode) with memory/RAG
  • Providing a Telegram-based assistant with an allowlist
  • Triggering agent workflows via HTTP webhooks

Not For

  • A lightweight single-purpose chatbot library (it is a full framework/runtime)
  • A turnkey hosted SaaS product with guaranteed SLAs (appears to be self-hosted)
  • A system that needs strict, documented API contracts like an OpenAPI-first service (docs are oriented to configuration and usage)

Interface

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

Authentication

Methods: Configure LLM provider API keys in preferences/runtime-config.json Dashboard password (temporary admin password on first start; optional BOT_DASHBOARD_ADMIN_PASSWORD) Optional Telegram allowlist
OAuth: No Scopes: No

Authentication for the runtime (dashboard) is suggested via an admin password, but no details are provided here about token-based auth, user management, or scopes. Telegram security is mentioned via token + allowlist.

Pricing

Free tier: No
Requires CC: No

No hosted pricing tiers described.

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • Autonomous/scheduled execution (Auto Mode) can trigger tool actions; ensure confirmations and sandboxing are correctly configured.
  • Containerized browser tooling may require elevated capabilities/large shared memory; misconfiguration can cause failures or security risk.
  • MCP tool servers via stdio require careful process management; mismatched protocols/timeouts can cause tool-call failures.

Alternatives

Full Evaluation Report

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

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 2026-03-30.

8642
Packages Evaluated
17761
Need Evaluation
586
Need Re-evaluation
Community Powered