Ledgermind

pip install cognis-ledgermind
ledgermind scan .            # → prioritized findings in seconds

🔎 Example output

Real, reproducible output from the tool — runs offline:

$ ledgermind-emit --version
ledgermind 0.1.0

$ ledgermind-emit --help
usage: ledgermind [-h] [--version] {audit} ...

Local LLM cost & token forensics with anomaly detection.

positional arguments:
  {audit}
    audit     Audit an LLM request log (JSONL or JSON array).

options:
  -h, --help  show this help message and exit
  --version   show program's version number and exit

Blocks above are real ledgermind output — reproduce them from a clone.

Sample result format (illustrative values — run on your own data for real findings):

{
"finding": {
"id": "1234567890",
"category": "vulnerability",
"name": "Apache Log4j RCE",
"description": "A remote code execution vulnerability in Apache Log4j.",
"severity": "high",
"created_at": "2021-12-10T14:30:00Z"
},
"indicators": [
{
"type": "ip",
"value": "192.0.2.1"
},
{
"type": "domain",
"value": "example.com"
}
],
"recommendations": [
{
"text": "Update Apache Log4j to version 2.16.0 or later."
}
]
}

Usage — step by step

1. Install (Python 3.8+, stdlib only):

   pip install ledgermind
   

2. Audit an LLM request log (JSONL or JSON array) for cost, tokens, and anomalies:

   ledgermind audit logs.jsonl
   

   Reports totals plus cost-by-model and cost-by-API-key breakdowns.
3. Override pricing and tune anomaly sensitivity:

   ledgermind audit logs.jsonl --pricing custom_pricing.json --mad-threshold 3.0
   

   (--pricing is merged over the built-in defaults; --mad-threshold is the modified z-score cutoff.)
4. Read the output as JSON:

   ledgermind audit logs.jsonl --format json | jq '.total_cost_usd, .anomalies[]'
   

5. Gate CI / cron on spend anomalies — exit 2 when any anomaly is detected:

   ledgermind audit logs.jsonl --fail-on-anomaly || echo "LLM spend anomaly detected"
   

Contents

• Why ledgermind? · Features · Quick start · Example · Architecture · AI stack · How it compares · Integrations · Install anywhere · Related · Contributing

Why ledgermind?

Local LLM cost & token forensics proxy with anomaly detection — without standing up heavyweight infrastructure.

ledgermind is single-purpose, scriptable, and self-hostable: point it at a target, get prioritized results in the format your workflow already speaks (table · JSON · SARIF), gate CI on it, and let agents drive it over MCP.

Features

• ✅ Price Call
• ✅ Load Events
• ✅ Detect Anomalies
• ✅ Build Report
• ✅ Runs on Linux/macOS/Windows · Docker · devcontainer
• ✅ Ports in Python, JavaScript, Go, and Rust (ports/)

Quick start

pip install cognis-ledgermind
ledgermind --version
ledgermind scan .                       # scan current project
ledgermind scan . --format json         # machine-readable
ledgermind scan . --fail-on high        # CI gate (non-zero exit)

Example

$ ledgermind scan .
  [HIGH    ] LED-001  example finding             (./src/app.py)
  [MEDIUM  ] LED-002  another signal              (./config.yaml)

  2 findings · risk score 5 · 38ms

Architecture

flowchart LR
  IN[addresses + transactions] --> P[ledgermind<br/>cluster + trace]
  P --> OUT[sanctions xref / report]

Use it from any AI stack

ledgermind is interoperable with every popular way of using AI:

• MCP server — ledgermind mcp (Claude Desktop, Cursor, Cognis.Studio, uncensored-fleet)
• OpenAI-compatible / JSON — pipe ledgermind scan . --format json into any agent or LLM
• LangChain · CrewAI · AutoGen · LlamaIndex — wrap the CLI/JSON as a tool in one line
• CI / scripts — exit codes + SARIF for non-AI pipelines

How it compares

	Cognis ledgermind	BerriAI
Self-hostable, no account	✅	varies
Single command, zero config	✅	⚠️
JSON + SARIF for CI	✅	varies
MCP-native (AI agents)	✅	❌
Polyglot ports (JS/Go/Rust)	✅	❌
Open license	✅ COCL	varies

Built in the spirit of BerriAI/litellm, re-framed the Cognis way. Missing a credit? Open a PR.

Integrations

Pipes into your stack: SARIF for code-scanning, JSON for anything, an MCP server (ledgermind mcp) for AI agents, and a webhook forwarder for SIEM/Slack/Jira. See docs/INTEGRATIONS.md.

Install — every way, every platform

pip install "git+https://github.com/cognis-digital/ledgermind.git"    # pip (works today)
pipx install "git+https://github.com/cognis-digital/ledgermind.git"   # isolated CLI
uv tool install "git+https://github.com/cognis-digital/ledgermind.git" # uv
pip install cognis-ledgermind                                          # PyPI (when published)
docker run --rm ghcr.io/cognis-digital/ledgermind:latest --help        # Docker
brew install cognis-digital/tap/ledgermind                             # Homebrew tap
curl -fsSL https://raw.githubusercontent.com/cognis-digital/ledgermind/main/install.sh | sh

Linux	macOS	Windows	Docker	Cloud
scripts/setup-linux.sh	scripts/setup-macos.sh	scripts/setup-windows.ps1	docker run ghcr.io/cognis-digital/ledgermind	DEPLOY.md (AWS/Azure/GCP/k8s)

Related Cognis tools

• aegis — AI Agent Permission & Access Auditor — surfaces the lethal trifecta of credentials + injection + reach
• promptmirror — Prompt-injection & indirect-injection scanner for any LLM context input
• adversa — LLM red-team harness — OWASP LLM Top 10 + MITRE ATLAS attack packs
• guardpost — Runtime agent firewall — PII redaction, rate limits, policy enforcement
• hallumark — LLM hallucination & grounding auditor for RAG systems
• aicard — Auto-generated NIST AI RMF / EU AI Act Annex IV model & system cards

Explore the suite → 🗂️ all 170+ tools · ⭐ awesome-cognis · 🔗 cognis-sources · 🤖 uncensored-fleet · 🧠 engram

Contributing

PRs, new rules, and demo scenarios are welcome under the collaboration-pull model — see CONTRIBUTING.md and SECURITY.md.

⭐ If ledgermind saved you time, star it — it genuinely helps others find it.

Interoperability

{} composes with the 300+ tool Cognis suite — JSON in/out and a shared OpenAI-compatible /v1 backbone. See INTEROP.md for the suite map, composition patterns, and reference stacks.

License

Source-available under the Cognis Open Collaboration License (COCL) v1.0 — free for personal, internal-evaluation, research, and educational use; commercial / production use requires a license ([email protected]). See LICENSE.

---