Dashboard / Repos / Playbookd

Playbookd

C 70 completed
Library
unknown / go · tiny
39
Files
4,427
LOC
0
Frameworks
2
Languages
OverviewFiles & MetricsGit ActivityCall GraphSecurityReports

Pipeline State

completed
Run ID
#356036
Phase
done
Progress
1%
Started
Finished
2026-04-13 01:31:02
LLM tokens
0

Pipeline Metadata

Stage
Skipped
Decision
skip_scaffold_dup
Novelty
38.22
Framework unique
—
Isolation
—
Last stage change
2026-04-16 18:15:42
Deduplication group #48102
Member of a group with 1 similar repo(s) — canonical #1874 view group →
Top concepts (1)
Library
Repobility — same analyzer, your code, free for public repos · /scan/

🧪 Code Distillation

Browse all specs →
Function bodies →
0
Real LLM specs →
0
0.0% coverage
All specs →
0
LLM insights →
1

AI Prompt

Create a standalone Go library called playbookd designed to give AI agents procedural memory. The system should allow agents to learn tasks by storing and retrieving procedures. Key features to implement include hybrid search combining BM25 full-text search (using Bleve) and optional cosine vector search (using FAISS). It needs to support composite scoring that blends text relevance with Wilson confidence scoring. Furthermore, it should handle execution recording and reflection to improve playbooks over time. Please also include support for multiple embedding providers like OpenAI, Google Gemini, and Ollama, and expose a CLI tool to manage the playbook store.
go ai-agent procedural-memory search bleve faiss cli
Generated by gemma4:latest

Catalog Information

playbookd is a standalone Go library that gives AI agents the ability to learn how to perform tasks and improve over time by storing and retrieving procedural knowledge.

Description

playbookd is a procedural memory system for AI agents, allowing them to learn from existing playbooks and improve their performance over time. It uses a combination of full-text search and vector search to find relevant procedures, and allows agents to record and reflect on their experiences to refine the playbook. The library also supports embedding providers such as OpenAI, Google Gemini, and Ollama.

الوصف

هو نظام ذاكرة إجرائية للمعاقص الذكية، يسمح لهم بالتعلم من المخططات القائمة وتحسين أدائهم مع الوقت. يستخدم نظام playbookd kombinasi من البحث عن النص الكامل والبحث عن الفيضانات للكشف عن الإجراءات ذات الصلة، ويسمح للمعاقص بمراجعة وتأمل تجاربهم لتعزيز المخطط. كما يدعم نظام playbookd مقدمي التضمين مثل OpenAI و Google Gemini و Ollama.

Novelty

9/10

Tags

procedural-memory ai-agents playbook-storage hybrid-search vector-search embedding-providers

Technologies

ent

Claude Models

claude-opus-4.6

Quality Score

C
69.9/100
Structure
58
Code Quality
89
Documentation
63
Testing
40
Practices
77
Security
90
Dependencies
50

Strengths

  • Well-documented README with substantial content
  • Good test coverage (32% test-to-source ratio)
  • Consistent naming conventions (snake_case)
  • Good security practices \u2014 no major issues detected

Weaknesses

  • No LICENSE file \u2014 legal ambiguity for contributors
  • No CI/CD configuration \u2014 manual testing and deployment
  • Potential hardcoded secrets in 1 files
  • 188 duplicate lines detected \u2014 consider DRY refactoring

Recommendations

  • Add a test suite \u2014 start with critical path integration tests
  • Set up CI/CD (GitHub Actions recommended) to automate testing and deployment
  • Add a linter configuration to enforce code style consistency
  • Add a LICENSE file (MIT recommended for open source)
  • Move hardcoded secrets to environment variables or a secrets manager

Security & Health

5.1h
Tech Debt (C)
A
OWASP (100%)
PASS
Quality Gate
Provenance: Repobility (https://repobility.com) — every score reproducible from /scan/
A
Risk (3)
Unknown
License
6.6%
Duplication
Full Security Report AI Fix Prompts SARIF SBOM

Languages

go
86.5%
markdown
13.5%

Frameworks

None detected

Concepts (1)

Analysis by Repobility (https://repobility.com) · MCP-ready
CategoryNameDescriptionConfidence
Repobility · MCP-ready · https://repobility.com
auto_categoryLibrarylibrary60%

LLM Insights

A standalone Go library enabling AI agents to learn and improve task performance by storing and retrieving procedural knowledge.structured_summary
info
purpose: A standalone Go library enabling AI agents to learn and improve task performance by storing and retrieving procedural kn
primary_domain: ml-training
reference_quality85
reuse_potential: high

Quality Timeline

1 quality score recorded.

View File Metrics
Repobility analyzer · published findings · https://repobility.com

Embed Badge

Add to your README:

![Quality](https://repos.aljefra.com/badge/80163.svg)
Quality BadgeSecurity Badge
Export Quality CSVDownload SBOMExport Findings CSV