Skip to main content
Glama
base76-research-lab

cognos-session-memory

by base76-research-lab
OverviewSchemaRelated ServersScoreDiscussions
Python
Local

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: Recall

Solution

A plan-mode gateway that:

  1. Extracts structured context from 3-5 recent traces

  2. Scores context quality via CognOS epistemic formula: C = p · (1 − Ue − Ua)

  3. Injects as system prompt only if C > threshold

  4. Flags for manual review if C < threshold

  5. Audits 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 review

Core 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 flag

  • force — always inject (for testing)

  • dry_run — compute score but never inject

Claude Code Integration

As a /compact replacement

# 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.

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

save_session(summary, project?)

Trust-score and persist a session summary

load_session(threshold?)

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 8788

Test /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=src

Documentation

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

Available Tools

2 tools
load_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.

ParametersJSON Schema
NameRequiredDescriptionDefault
thresholdNoMinimum trust score to accept (default 0.45).

TDQS

A4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description carries full burden. It discloses that it only returns context passing trust threshold, never injects low-confidence or stale sessions, and returns summary and block. However, it does not specify behavior when no session exists or error conditions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences with no redundancy. First sentence states action and expected output; second adds critical constraint. Fully front-loaded and efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple tool with one optional parameter and no output schema, the description covers purpose, return values, and trust threshold. It is complete enough for an agent to use correctly, though it omits edge cases like missing session.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the description adds minimal new insight beyond the schema. It reinforces the threshold's role but does not elaborate on format or usage semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states 'Load' action on 'last verified session context from CognOS Session Memory' and specifies output: summary and inject-ready block. It distinguishes from sibling 'save_session' by verb and scope, and adds constraint about trust threshold.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Description implies use for retrieving a verified session context but does not explicitly state when not to use or alternative tools. It mentions trust threshold but lacks exclusionary guidance such as 'use save_session to create a session'.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

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.

ParametersJSON Schema
NameRequiredDescriptionDefault
summaryYesCompact session summary (100-200 words): active project, last decision, current output, open questions, key files.
projectNoOptional: active project name.

TDQS

A4.6/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description fully carries the burden of behavioral disclosure. It reveals that summaries are 'epistemically scored', that low-scored summaries may not be injected next session, and that the operation saves to persistent memory. No contradictions noted.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description consists of two compact sentences. The first sentence states the core purpose, and the second adds essential behavioral context. No redundant or unnecessary information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (2 parameters, no output schema), the description is nearly complete. It explains the trust scoring mechanism and injection eligibility. However, it does not mention what the tool returns (if anything) or potential error conditions, which would be helpful but not critical for a save operation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with descriptions for both parameters, but the tool's description adds extra semantic value beyond the schema: it specifies the recommended word count range (100-200 words) and content guidelines for the 'summary' parameter ('active project, last decision, current output, open questions, key files'). The 'project' parameter is correctly noted as optional.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Save' and the resource 'trust-scored session summary to CognOS Session Memory'. It distinguishes from the sibling tool 'load_session' by implying the opposite action (save vs load), and also mentions an alternative ('/compact') for context.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly says when to use this tool ('instead of or after /compact to preserve verified context across sessions') and provides a guideline on summary quality ('short or vague summaries get lower trust scores and may not be injected next session'). It does not explicitly state when not to use it, but the context is clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. 2 tool updatesv0.1.0
    • First observedload_session
    • First observedsave_session
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4.1/5.0
Disambiguation5/5

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.

Naming Consistency5/5

Both tools follow a consistent verb_noun pattern (load_session, save_session), which is clear and predictable. No mixing of conventions.

Tool Count3/5

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.

Completeness3/5

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

ActivityInactive
ResponsivenessSyncing

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

  • ai-memory-mcp

    zhanpu89
    A
    license
    A
    quality
    D
    maintenance
    Provides persistent session memory for AI assistants, enabling them to store, search, and retrieve conversation summaries across sessions via the Model Context Protocol.
    10
    MIT

  • Recall

    joseairosa
    A
    license
    Not graded
    quality
    C
    maintenance
    Provides persistent, cross-session memory for AI agents, allowing them to store and automatically retrieve information across different conversations and sessions without repeating context.
    15
    175
    MIT

  • Memento

    diego-ninja
    A
    license
    Not graded
    quality
    D
    maintenance
    Persistent memory system for LLMs with lossless transcript management, enabling memory recall and full session history search across all conversations.
    45
    MIT

  • Memento

    scrypster
    A
    license
    Not graded
    quality
    C
    maintenance
    Provides persistent memory for AI tools by building a local knowledge graph from conversations, enabling cross-session recall and context awareness without cloud dependencies.
    9
    MIT

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/base76-research-lab/cognos-session-memory'

If you have feedback or need assistance with the MCP directory API, please join our Discord server