loop-engineering
Skill2 starsChanged 5 months agoMITView on GitHub
Implement ODAEU harness loops, RAG evolve tuning, and procedural memory in LoopForge or similar systems. Use when building self-improving agents, eval gates, MCP tool bridges, or RAG version trees.
33 other projects use a version of this.
Adopted by
Most recently taken up by
- vpeetla-ai/venkat-ai-platformword for word, first seen Nov 8, 2026
- Mark393295827/graph-engineering-architecturestheir own version, first seen Nov 8, 2026
- victor-hac-work/loop-engineering-skillstheir own version, first seen Nov 8, 2026
- jggomez/expert-ai-developer-skillstheir own version, first seen Nov 6, 2026
- Hakkadaikon/hymmetheir own version, first seen Oct 26, 2026
- vpeetla-ai/swarm-agent-patternword for word, first seen Oct 20, 2026
Other versions33 projects use a version of this.
Word for word · 5
- vpeetla-ai/aegisai-enterprise-agent-platform★ 2100% same
- vpeetla-ai/multi-agent-system-pattern★ 2100% same
- vpeetla-ai/react-agent-pattern★ 2100% same
- vpeetla-ai/swarm-agent-pattern★ 2100% same
- vpeetla-ai/venkat-ai-platform★ 2100% same
Edited · 0
None found.
Wrote their own version · 28
- bojieli/ai-agent-book-projects★ 53ksame name
- bojieli/ai-agent-book★ 53ksame name
- huytieu/COG-second-brain★ 1.3ksame name
- akitaonrails/my-skills★ 283same name
- jggomez/expert-ai-developer-skills★ 31same name
- aiconnai/agentshield★ 21same name
- sxivansx/loop-engineering★ 10same name
- victor-hac-work/loop-engineering-skills★ 5same name
- Mark393295827/graph-engineering-architectures★ 4same name
- aiconnai/engram★ 3same name
18 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository13 other files it gives its agents.
- AGENTS.mdAGENTS.md
- aegis-gatewaySkill
- agentic-engineeringSkill
- deploy-vercel-renderSkill
- governed-ai-stackSkill
- grill-with-contextSkill
- hitl-side-effectsSkill
- langgraph-orchestrationSkill
- portfolio-adrSkill
- rag-governanceSkill
- repo-fix-prSkill
- setup-vpeetla-skillsSkill
- tdd-agent-loopsSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 22 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 36
Never give agents raw shell without allowlist
“Common” is measured: kept by at least 6 in 10 of the 22 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Loop Engineering
ODAEU outer loop
| Phase | Action |
| Observe | Load RAG config vN, memory hints, corpus context |
| Decide | Plan ReAct steps or orchestrator decomposition |
| Act | MCP tools (read_file, search_docs) or repo patches |
| Evaluate | Recall, faithfulness, pytest, review score |
| Update | Tune RAG (top_k, hybrid_alpha) + write lesson |
RAG evolve signals
| Failure | Tune |
| low_recall | ↑ top_k, ↑ hybrid_alpha |
| low_faithfulness | ↑ rerank_threshold, ↓ hybrid_alpha |
Memory
Lesson(failure_mode, lesson, rag_version)→ JSON store (v1)- Hints injected on next run via
hints_for_query
MCP bridge
- Local adapters in
mcp/bridge.py; extensible to stdio MCP servers - Never give agents raw shell without allowlist
Reference
loop-engine-agent-platform/src/loop_engine/harness/loops/support-intelligence.yaml- ADR-001 in LoopForge repo
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.