Power your agent
คำสั่งของผู้เผยแพร่เอง ไม่ใช่เอนด์พอยต์ของ PlugMCP
Host a copy with our keys and logs.
uvx cognos-session-memory-mcp==0.1.0Claude Code ไม่มีลิงก์ติดตั้งสำหรับคำสั่งแบบโลคัล ให้คัดลอกคำสั่งด้านล่างแล้วรันในเทอร์มินัล
COGNOS_TRACE_DB=<value> claude mcp add io.github.base76-research-lab-cognos-session-memory -- uvx cognos-session-memory-mcp==0.1.0รันในเทอร์มินัล
{ "mcpServers": { "io.github.base76-research-lab-cognos-session-memory": { "command": "uvx", "args": [ "cognos-session-memory-mcp==0.1.0" ], "env": { "COGNOS_TRACE_DB": "<value>" } } }}claude_desktop_config.json
URL แบบรีโมตหรือคำสั่งบนเครื่องของคุณ? การติดตั้งสองแบบต่างกันอย่างไร
รันบน PlugMCP
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
เปิดจากผู้เผยแพร่
mcp-name: io.github.base76-research-lab/cognos-session-memory
Verified context injection via epistemic trust scoring for LLMs.
Solves session fragmentation by maintaining verified, high-confidence session context between conversations.
CognOS trust scoring (C=p·(1-Ue-Ua)) and session trace storage as MCP tools.
Large language models suffer from session fragmentation: each new conversation starts without verified context of previous work. This forces repeated explanations, loses decision history, and breaks long-running workflows.
Existing solutions (persistent memory systems, vector retrieval) either:
A plan-mode gateway that:
C = p · (1 − Ue − Ua)C > thresholdC < thresholdrecent_traces (n=5)
↓
extract_context() → ContextField + coverage
↓
compute_trust_score(p, ue, ua) → C, R, decision
↓
if C > threshold:
system_prompt ← inject
else:
flagged_reason ← manual review
C = p · (1 − Ue − Ua)
R = 1 − C
where:
p = prediction confidence (coverage of required fields)
Ue = epistemic uncertainty (divergence between traces)
Ua = aleatoric uncertainty (mean risk in traces)
R < 0.25 → PASS (inject without review)
0.25 ≤ R < 0.60 → REFINE (inject with caution)
R ≥ 0.60 → ESCALATE (flag for manual review)
Extract and score context.
Request:
{
"n": 5,
"trust_threshold": 0.75,
"mode": "auto"
}
Response (if injected):
{
"status": "injected",
"trust_score": 0.82,
"confidence": 0.82,
"risk": 0.18,
"decision": "PASS",
"context": {
"active_project": "CognOS mHC research",
"last_decision": "Verify P1 hypothesis",
"open_questions": ["How does routing entropy scale?"],
"current_output": "exp_008 complete",
"recent_models": ["gpt-4", "claude-3", "mistral"]
},
"system_prompt": "## CognOS Context...",
"trace_ids": ["uuid-1", "uuid-2", ...]
}
Response (if flagged):
{
"status": "flagged",
"trust_score": 0.45,
"decision": "REFINE",
"flagged_reason": "Trust score 0.45 below threshold 0.75. Manual review recommended.",
"trace_ids": [...]
}
trust_score ≥ threshold, else flag# In any Claude Code session:
/save
Claude writes a structured summary, trust-scores it, and persists it to SQLite.
Next session: automatically injected as SESSION_CONTEXT before your first prompt.
See docs/COMPACT_ALTERNATIVE.md for a full comparison.
Add to ~/.claude/settings.json:
{
"mcpServers": {
"cognos-session-memory": {
"command": "python3",
"args": ["/path/to/cognos-session-memory/mcp_server.py"]
}
}
}
Tools exposed:
git clone https://github.com/base76-research-lab/cognos-session-memory
cd cognos-session-memory
pip install -e .
python3 -m uvicorn --app-dir src main:app --port 8788
curl -X POST http://127.0.0.1:8788/v1/plan \
-H 'Content-Type: application/json' \
-d '{"n": 5, "mode": "dry_run"}'
curl -X POST http://127.0.0.1:8788/v1/plan \
-H 'Content-Type: application/json' \
-d '{"n": 5, "trust_threshold": 0.75, "mode": "auto"}'
save_session, load_session)pytest tests/ -v --cov=src
/compactSee docs/PAPER.md — "Verified Context Injection: Epistemically Scored Session Memory for Large Language Models"
Status: Independent research — Base76 Research Lab, 2026 Authors: Björn André Wikström (Base76)
@software{wikstrom2026cognos,
author = {Wikström, Björn André},
title = {{CognOS Session Memory}: Verified Context Injection via Epistemic Trust Scoring},
year = {2026},
url = {https://github.com/base76-research-lab/cognos-session-memory}
}
MIT
CognOS trust scoring (C=p·(1-Ue-Ua)) and session trace storage as MCP tools.
{ "mcpServers": { "io.github.base76-research-lab-cognos-session-memory": { "command": "uvx", "args": [ "cognos-session-memory-mcp==0.1.0" ], "env": { "COGNOS_TRACE_DB": "<value>" } } }}เครื่องมือ
ยังไม่มีรายการเครื่องมือ เซิร์ฟเวอร์แบบรีโมตจะได้รายการหลังการตรวจสอบสถานะครั้งแรก
FAQ
คัดลอกคอนฟิก stdio สำหรับ Cursor, Claude Desktop, Claude Code หรือ VS Code ได้ในหน้านี้ คอนฟิกนี้ใช้การติดตั้งของผู้เผยแพร่ ไม่ใช่พร็อกซีของ PlugMCP
ผู้เผยแพร่ระบุตัวแปรสภาพแวดล้อมเหล่านี้: COGNOS_TRACE_DB
Cognos Session Memory ทำงานแบบโลคัลผ่าน stdio
ตรวจสอบล่าสุดเมื่อ 2026-11-09 CognOS trust scoring (C=p·(1-Ue-Ua)) and session trace storage as MCP tools.