open/portfolio-optimiser
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity Actions
Generic, open framework on Microsoft Agent Framework (MAF): multi-agent cost-saving proposals gated by a mandatory deterministic validator, with HITL learning.
64 commits 1 branch 0 tags 830 KiB
  • Python 100%
Find a file
Kjell Tore Guttormsen 129a40baea docs(fot-i-bakken): ground-truth-verifisert levert-vs-lovet — agentiske lag inerte 
Fot i bakken før fase-valg (Fase 4 vs D7). Explore-agent kartla; hovedkontekst
selv-verifiserte de konsekvensrike funnene mot kildekoden:

- ExpeL-laeringssloyfa ER APEN: retrieval naar aldri modellen (generering run.py:194
  for retrieval run.py:216-221; sctx run.py:219 forkastes; 0 context_providers i src/).
- README 'Not yet usable' (README.md:5) motsier 'Fase 1-3 lukket' — release-blokkerende.
- Maker-checker-checker gater ingenting (modulo-selector workflow.py:93-96).
- Ingen ekte-modell-kjoring (alle 4 skip = live-provider). Ingen SKILL.md. Ingen entry-point.

Deterministisk ryggrad (validator/budsjett/provenance/sti-sikkerhet/onboarding) holder.
Neste: operatorbeslutning — lukk kjerne-gjeld (A) vs aerlig nedgrader+release (B).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_019any9zfGNNwWJPX5Zq2QRz
2026-06-26 15:25:03 +02:00
.claude/projects docs(fase3): remediation plan for the 2 /trekreview MAJOR findings (F1+F2) 2026-06-26 15:07:48 +02:00
docs docs(fot-i-bakken): ground-truth-verifisert levert-vs-lovet — agentiske lag inerte 2026-06-26 15:25:03 +02:00
spikes fix(fase1): spike B fan-out measures real conversation bleed, not a counter 2026-06-24 11:09:55 +02:00
src/portfolio_optimiser fix(fase3): stamp real proposer model into provenance, kill fake-model leak (F1) 2026-06-26 15:03:45 +02:00
tests test(fase3): portfolio rejection arm + provenance-seam assertions (F2 + F1 follow-up) 2026-06-26 15:05:41 +02:00
.gitignore docs(fase2): /trekbrief — gated MVP vertical-slice brief (6/6) [skip-docs] 2026-06-24 11:56:57 +02:00
.python-version feat: initial scaffold (Python framework on Microsoft Agent Framework) 2026-06-23 22:01:22 +02:00
CHANGELOG.md feat: initial scaffold (Python framework on Microsoft Agent Framework) 2026-06-23 22:01:22 +02:00
CLAUDE.md build(fase1): add dev orchestration + solver + async deps, scaffold spikes 2026-06-24 09:57:57 +02:00
env.template docs(fase2): add env.template documenting both profiles + no-egress notes 2026-06-26 00:43:26 +02:00
pyproject.toml docs(fase2): record PEP 735 dependency-groups as intentional Step 1 deviation 2026-06-26 00:43:46 +02:00
README.md feat: initial scaffold (Python framework on Microsoft Agent Framework) 2026-06-23 22:01:22 +02:00
uv.lock build(fase2): promote orchestrations + pulp to core deps 2026-06-24 13:22:04 +02:00

README.md

portfolio-optimiser

Generic, open framework on Microsoft Agent Framework (MAF) for finding cost-savings / efficiency proposals within each project of a portfolio of independent projects. Multiple agents collaborate to generate candidate proposals; a mandatory deterministic validator (solver + Monte Carlo) decides the numbers; domain experts review via human-in-the-loop, and the system learns from their verdicts.

Status: Early development (plan phase). Not yet usable.

Disclaimer — technical framework only. This project is a technical framework. Organizations that deploy it are themselves responsible for ensuring a valid processing purpose and for any required assessments (DPIA, risk/ROS, security reviews, etc.). The framework ships technical affordances (local-only mode, provenance/audit logging, no silent data egress) to enable compliant use, but makes no compliance guarantees.

Design philosophy

The result will never fit any single customer 100%. The goal is a ~90% genuinely generic core plus clear extension points, so competent people can configure the last mile per customer. We deliberately do not chase the final 10%.

Docs

Stack

Python ≥3.10 · MAF (agent-framework) · uv. Backend profiles: Azure/Foundry (full) + local (fallback).

Develop

uv sync
uv run pytest
uv run ruff check .