cognos-session-memory
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@cognos-session-memory load last session's verified context"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
CognOS Session Memory
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.
Problem
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:
Lack trust scores before injection → hallucinations propagate
Don't audit which context was injected → compliance gaps
Treat all past information equally → noise overwhelms signal
Related MCP server: Memento
Solution
A plan-mode gateway that:
Extracts structured context from 3-5 recent traces
Scores context quality via CognOS epistemic formula:
C = p · (1 − Ue − Ua)Injects as system prompt only if
C > thresholdFlags for manual review if
C < thresholdAudits every context injection with trace IDs → EU AI Act compliance
Architecture
recent_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 reviewCore Formula
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)Action Gate
R < 0.25 → PASS (inject without review)
0.25 ≤ R < 0.60 → REFINE (inject with caution)
R ≥ 0.60 → ESCALATE (flag for manual review)API
POST /v1/plan
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": [...]
}Modes
auto (default) — inject if
trust_score ≥ threshold, else flagforce — always inject (for testing)
dry_run — compute score but never inject
Claude Code Integration
As a /compact replacement
# In any Claude Code session:
/saveClaude 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.
As an MCP server
Add to ~/.claude/settings.json:
{
"mcpServers": {
"cognos-session-memory": {
"command": "python3",
"args": ["/path/to/cognos-session-memory/mcp_server.py"]
}
}
}Tools exposed:
Tool | Description |
| Trust-score and persist a session summary |
| Retrieve last verified context (default threshold: 0.45) |
Quick Start
Installation
git clone https://github.com/base76-research-lab/cognos-session-memory
cd cognos-session-memory
pip install -e .Run Gateway
python3 -m uvicorn --app-dir src main:app --port 8788Test /v1/plan (dry_run)
curl -X POST http://127.0.0.1:8788/v1/plan \
-H 'Content-Type: application/json' \
-d '{"n": 5, "mode": "dry_run"}'Test /v1/plan (auto)
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"}'Modules
trust.py — CognOS confidence formula, action gate, signal extractors
trace_store.py — SQLite persistence (write/read/purge)
plan.py — Context extraction, trust scoring, system prompt building
main.py — FastAPI gateway + middleware
mcp_server.py — MCP stdio server (
save_session,load_session)
Testing
pytest tests/ -v --cov=srcDocumentation
COMPACT_ALTERNATIVE.md — Why this beats
/compactPAPER.md — Research paper
Research Paper
See 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)
Citation
@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}
}License
MIT
Contact
Author: Björn André Wikström
Email: bjorn@base76.se
ORCID: 0009-0000-4015-2357
GitHub: base76-research-lab
Available Tools
2 toolsload_sessionA
Load the last verified session context from CognOS Session Memory. Returns the summary and an inject-ready SESSION_CONTEXT block. Only returns context that passed the trust threshold — never injects low-confidence or stale sessions.
Inputs: threshold.
save_sessionA
Save a trust-scored session summary to CognOS Session Memory. Call this instead of or after /compact to preserve verified context across sessions. The summary is scored epistemically — short or vague summaries get lower trust scores and may not be injected next session.
Inputs: summary (required), project.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 2 tools
The two tools have completely distinct purposes: load_session retrieves context and save_session stores it. There is no overlap in their functionality, making it easy for an agent to select the correct one.
Both tools follow a consistent verb_noun pattern (load_session, save_session), which is clear and predictable. No mixing of conventions.
With only 2 tools, the surface is thin for a memory management system. While it covers the basic load/save operations, the count is borderline low for the implied scope.
The tool set covers loading and saving sessions, but lacks operations like list, delete, or update sessions. There are notable gaps that may require agents to work around missing functionality.
Maintenance
Related MCP Connectors
Cross-LLM persistent memory: store context once, recall it from any AI model.
Self-curating memory your AI tools share: provenance, verified citations, and trust tiers.
Memory for deep conversational context across any platform
Persistent memory layer for AI clients: store, recall, and correct context across tools.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceProvides persistent, cross-session memory for AI agents, allowing them to store and automatically retrieve information across different conversations and sessions without repeating context.54 npm179MIT
- AlicenseNot gradedqualityDmaintenanceProvides persistent memory for AI tools by building a local knowledge graph from conversations, enabling cross-session recall and context awareness without cloud dependencies.9MIT
- AlicenseNot gradedqualityDmaintenanceProvides AI agents with persistent memory across sessions, enabling recall of decisions, clients, and deadlines with verifiable citations.MIT
- AlicenseNot gradedqualityBmaintenanceProvides AI agents a shared long-term memory layer with evidence-backed, auditable claims, enabling persistent, explainable, and conflict-aware recall across sessions.18 PyPI8MIT