Files

T

Krystie 9d8a90b895 Rename project: ump-recall -> self-directed-learning

- package.json: name + description updated
- README.md: full rewrite framing as Hermes/Krystie self-improvement loop
- scripts/judge.py: triadic review (Claude + Codex via Hermes OAuth) — replaces broken OpenAI API path
- src/ump-recall-mcp.js: MCP initialize handshake fix — pre-init tools/call no longer times out
- New Gitea repo: sami7777/self-directed-learning (old ump-recall retained for reference)

2026-07-12 23:13:55 -07:00

2.5 KiB

Raw Permalink Blame History

self-directed-learning

Self-directed learning framework for Hermes / Krystie — multi-strategy retrieval over UMP memory, with skill detection, decay, and triadic review.

What this is

A continuous-learning loop for AI agents:

Retrieval substrate — multi-strategy (FTS5 + vector + graph) RRF fusion with ACT-R re-ranking, served as an MCP shim so Hermes/Krystie can use it transparently through their existing UMP tool surface.
Memory hygiene — nightly decay (per-kind rates, atomic writes, automatic backups), access tracking (frequency + last_accessed_at) feeding the decay and re-ranker.
Knowledge graph — entity extraction + typed relations + co-occurrence edges; BFS expansion surfaces related URNs even when the direct text doesn't match.
Triadic review — Claude + Codex (via Hermes OAuth / ChatGPT Pro subscription) as independent judges for claims before they're written to long-term memory.
Cron-driven framework — skill gap detection, spaced repetition, foraging, reflective journaling, self-measure. All run autonomously and feed back into the retrieval substrate.

Phases shipped

Phase	What	Tests
1	Sidecar on `:4380` + 3-channel RRF	baseline 0.500 → 1.000 (+50pp)
2	Graph channel (typed relations + co-occurrence)	12 unique top-5 graph-only wins
3	ACT-R re-ranker	84% top-5 retention, 4/20 #1 changes
4	Decay script	20/20 tests, nightly cron
5	Access tracking	28/28 tests, feeds decay + re-ranker
6	Co-occurrence edges (in code)	(tests pending)
7	Triadic review (judge.py)	Claude + Codex wired

Stack

Language: Node.js 18+ (sidecar, MCP shim), Python 3.11+ (decay, framework scripts)
Dependencies: UMP (@universalmemoryprotocol/core 0.1.0), Ollama (snowflake-arctic-embed2 1024-dim), Qdrant (memories_ump collection), Express, undici, MCP SDK 1.29.
Repo: http://100.81.59.99/sami7777/self-directed-learning (DNS3 Gitea)
Local path: /root/ump-recall/ (directory name kept for stability of running processes; only the repo was renamed)

Run

npm start                          # sidecar on :4380
node src/ump-recall-mcp.js         # MCP shim (stdio)
python3 scripts/ump_decay.py --apply    # nightly decay
python3 scripts/judge.py --claim "..."  # Claude + Codex review
npm test                           # full test suite

Architecture

See /root/.hermes/skills/autonomous-ai-agents/agent-self-improvement-framework/ for the full framework spec.

2.5 KiB Raw Permalink Blame History