Skip to main content

Minimal, verifiable implementation of persistent long-term memory for AI agents

Project description

๐Ÿง  Cognitive Kernel

๐Ÿ‡ฐ๐Ÿ‡ท ํ•œ๊ตญ์–ด | ๐Ÿ‡บ๐Ÿ‡ธ English

Minimal, verifiable implementation of persistent long-term memory for AI agents.

๊ธฐ์–ต์˜ ์‹œ๊ฐ„ ์ธ์ฝ”๋”ฉ(Temporal Encoding), ์ค‘์š”๋„ ๋žญํ‚น(Importance Ranking), ์˜์‚ฌ๊ฒฐ์ • ๋ฐ˜์˜(Decision Impact)์„ ๊ฒฐํ•ฉํ•œ ๋ชจ๋“ˆํ˜• ์ธ์ง€ ํ”„๋ ˆ์ž„์›Œํฌ.


๐ŸŽฏ ์™œ ์ง€๊ธˆ ํ•„์š”ํ•œ๊ฐ€?

ํ˜„๋Œ€ LLM ์—์ด์ „ํŠธ์—๋Š” ๊ตฌ์กฐํ™”๋œ ์žฅ๊ธฐ ๊ธฐ์–ต๊ณผ ์‹คํ–‰ ์ œ์–ด ๊ธฐ๋Šฅ์ด ๋ถ€์กฑํ•ฉ๋‹ˆ๋‹ค.

Cognitive Kernel์€ ์ด ๊ฐญ์„ ๋ฉ”์šฐ๊ธฐ ์œ„ํ•œ drop-in ์ธ์ง€ ์„œ๋ธŒ์‹œ์Šคํ…œ์„ ์ œ๊ณตํ•ฉ๋‹ˆ๋‹ค.

โš ๏ธ ์—ฐ๊ตฌ ๋ฐ ์‹คํ—˜ ๋„๊ตฌ์ž…๋‹ˆ๋‹ค.
   ์‹ค์ œ ๋‡Œ์˜ ์™„์ „ํ•œ ๋ชจ๋ธ์ด ์•„๋‹ˆ๋ฉฐ, ์ž„์ƒ ์ง„๋‹จ ๋„๊ตฌ๊ฐ€ ์•„๋‹™๋‹ˆ๋‹ค.

๐Ÿ“Œ This project does not claim biological equivalence to human memory.
   It provides a computer-science definition of long-term memory:
   persistent, structured, recallable, and decision-impacting.

โญ ํ•ต์‹ฌ ๊ธฐ๋Šฅ: 3์ค„๋กœ ์‹œ์ž‘ํ•˜๋Š” ์žฅ๊ธฐ ๊ธฐ์–ต

from cognitive_kernel import CognitiveKernel

with CognitiveKernel("my_brain") as kernel:
    kernel.remember("meeting", {"topic": "project"}, importance=0.9)
    memories = kernel.recall(k=5)           # PageRank ๊ธฐ๋ฐ˜ ์ค‘์š”๋„ ํšŒ์ƒ
    decision = kernel.decide(["rest", "work"])  # Softmax ์˜์‚ฌ๊ฒฐ์ •
# ์ž๋™ ์ €์žฅ๋จ โ†’ ํ”„๋กœ์„ธ์Šค ์ข…๋ฃŒ ํ›„์—๋„ ๊ธฐ์–ต ์œ ์ง€

โœ… ์ด๊ฒƒ๋งŒ์œผ๋กœ:

๊ธฐ๋Šฅ ์„ค๋ช… ์•Œ๊ณ ๋ฆฌ์ฆ˜
remember() ๊ธฐ์–ต ์ €์žฅ (์žฅ๊ธฐ ๊ธฐ์–ต) ์‹œ๊ฐ„์ถ• ์ €์žฅ + ์ž๋™ ์˜์†์„ฑ
recall() ์ค‘์š”ํ•œ ๊ธฐ์–ต ํšŒ์ƒ Google PageRank
decide() ์˜์‚ฌ๊ฒฐ์ • Softmax Utility

โ†’ ์žฅ๊ธฐ ๊ธฐ์–ต ์ƒ์„ธ ์„ค๋ช…


๐Ÿ“ ํ•ต์‹ฌ ์ˆ˜์‹

1. ๊ธฐ์–ต ์ค‘์š”๋„ (MemoryRank)

Personalized PageRank ์•Œ๊ณ ๋ฆฌ์ฆ˜:

$$ \mathbf{r}^{(t+1)} = \alpha \cdot M \cdot \mathbf{r}^{(t)} + (1-\alpha) \cdot \mathbf{v} $$

  • $\mathbf{r}$: ๊ธฐ์–ต ์ค‘์š”๋„ ๋ฒกํ„ฐ
  • $M$: ๊ธฐ์–ต ์ „์ด ํ–‰๋ ฌ (์—ด ์ •๊ทœํ™”)
  • $\alpha$: ๊ฐ์‡  ๊ณ„์ˆ˜ (๊ธฐ๋ณธ๊ฐ’: 0.85)
  • $\mathbf{v}$: ๊ฐœ์ธํ™” ๋ฒกํ„ฐ (recency, emotion, frequency ๊ฐ€์ค‘์น˜)

2. ์‹œ๊ฐ„ ๊ฐ์‡  (Panorama)

์ง€์ˆ˜ ๊ฐ์‡  ํ•จ์ˆ˜:

$$ S(t) = S_0 \cdot e^{-\lambda \cdot \Delta t}, \quad \lambda = \frac{\ln 2}{t_{1/2}} $$

  • $S(t)$: ์‹œ๊ฐ„ $t$์—์„œ์˜ ์ค‘์š”๋„
  • $t_{1/2}$: ๋ฐ˜๊ฐ๊ธฐ (๊ธฐ๋ณธ๊ฐ’: 3600์ดˆ = 1์‹œ๊ฐ„)

3. ์˜์‚ฌ๊ฒฐ์ • (PFC)

Softmax ์„ ํƒ ํ™•๋ฅ :

$$ P(a_i) = \frac{e^{U(a_i) / T}}{\sum_j e^{U(a_j) / T}} $$

  • $U(a)$: ํ–‰๋™ $a$์˜ ํšจ์šฉ = ๊ธฐ๋Œ€๋ณด์ƒ - ๋น„์šฉ - ์œ„ํ—˜
  • $T$: ์˜จ๋„ (ํƒ์ƒ‰ vs ์ฐฉ์ทจ ๊ท ํ˜•)

โ†’ ์ด๋ก ์  ๊ธฐ๋ฐ˜ ์ƒ์„ธ


๐Ÿ’พ ์žฅ๊ธฐ ๊ธฐ์–ต์ด๋ž€?

์ปดํ“จํ„ฐ ๊ณตํ•™์  ์ •์˜

์˜์†์„ฑ(Persistence): ํ”„๋กœ์„ธ์Šค ์ข…๋ฃŒ ํ›„์—๋„ ๋ฐ์ดํ„ฐ๊ฐ€ ์œ ์ง€๋จ

Cognitive Kernel์˜ ๊ตฌํ˜„

์„ธ์…˜ A (ํ”„๋กœ์„ธ์Šค 1)          ์„ธ์…˜ B (ํ”„๋กœ์„ธ์Šค 2)
โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€      โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€
kernel.remember(...)  โ†’    ํŒŒ์ผ ์ €์žฅ
        โ†“                       โ†“
ํ”„๋กœ์„ธ์Šค ์ข…๋ฃŒ              CognitiveKernel("my_brain")
                                โ†“
                           ์ž๋™ ๋กœ๋“œ โ†’ ๊ธฐ์–ต ๋ณต๊ตฌ!

์ €์žฅ ๊ตฌ์กฐ

.cognitive_kernel/my_brain/
โ”œโ”€โ”€ panorama.json      # ์‹œ๊ฐ„์ถ• ์ด๋ฒคํŠธ (๊ธฐ์–ต ๋ฐ์ดํ„ฐ)
โ”œโ”€โ”€ memoryrank.json    # ์ค‘์š”๋„ ๊ทธ๋ž˜ํ”„
โ”œโ”€โ”€ edges.json         # ๊ธฐ์–ต ์—ฐ๊ฒฐ ๊ด€๊ณ„
โ”œโ”€โ”€ q_values.json      # ์Šต๊ด€ ํ•™์Šต (Q-Learning)
โ””โ”€โ”€ meta.json          # ์„ธ์…˜ ๋ฉ”ํƒ€๋ฐ์ดํ„ฐ

โ†’ ์žฅ๊ธฐ ๊ธฐ์–ต ๊ธฐ์ˆ  ๋ฌธ์„œ


๐Ÿงช ํ…Œ์ŠคํŠธ ๊ฒฐ๊ณผ

์žฅ๊ธฐ ๊ธฐ์–ต ์ฆ๋ช…

# ํ…Œ์ŠคํŠธ ์‹คํ–‰
cd /Users/jazzin/Desktop/00_BRAIN/Cognitive_Kernel
python3 cognitive_kernel.py

๊ฒฐ๊ณผ:

๐Ÿ“ฆ Session: test_session
๐Ÿ“ ๊ธฐ์–ต ์ €์žฅ... 3๊ฐœ
๐Ÿ” ๊ธฐ์–ต ํšŒ์ƒ (Top 3): idea(0.349), conversation(0.333), meeting(0.318)
๐ŸŽฏ ์˜์‚ฌ๊ฒฐ์ •: rest (ํšจ์šฉ: 0.250)
โœ… ์ž๋™ ์ €์žฅ ์™„๋ฃŒ!

๐Ÿ”„ ์„ธ์…˜ ๋ณต๊ตฌ ํ…Œ์ŠคํŠธ...
   ๋ณต๊ตฌ๋œ ์ด๋ฒคํŠธ: 3๊ฐœ โ† ํ”„๋กœ์„ธ์Šค ์ข…๋ฃŒ ํ›„์—๋„ ์œ ์ง€๋จ!

7๊ฐœ ์—”์ง„ ํ†ตํ•ฉ ์‹œ๋ฎฌ๋ ˆ์ด์…˜

์‹œ๋‚˜๋ฆฌ์˜ค Stress Max Hyperarousal Efficiency Alerts
Normal Day 0.44 1ํšŒ 0.71 1๊ฐœ
PTSD 0.80 3ํšŒ 0.61 5๊ฐœ

โ†’ ์ „์ฒด ํ…Œ์ŠคํŠธ ๊ฒฐ๊ณผ


๐Ÿ“ฆ ์ „์ฒด ๋ชจ๋“ˆ ๊ตฌ์„ฑ

๋ชจ๋“ˆ ์—ญํ•  ํ•ต์‹ฌ ์•Œ๊ณ ๋ฆฌ์ฆ˜ ์˜์†์„ฑ
MemoryRank ๊ธฐ์–ต ์ค‘์š”๋„ PageRank โœ… JSON/NPZ
Panorama ์‹œ๊ฐ„์ถ• ๊ธฐ์–ต Exponential Decay โœ… JSON/SQLite
PFC ์˜์‚ฌ๊ฒฐ์ • Softmax Utility
BasalGanglia ์Šต๊ด€ ํ•™์Šต TD-Learning โœ… Q-values
Amygdala ๊ฐ์ •/์œ„ํ˜‘ Rescorla-Wagner
Hypothalamus ์—๋„ˆ์ง€/์ŠคํŠธ๋ ˆ์Šค HPA Dynamics
Thalamus ์ž…๋ ฅ ํ•„ํ„ฐ๋ง Salience Gating

๐Ÿ”ง ํ™œ์šฉ ๋ฐฉํ–ฅ

๐Ÿ”ฌ ์—ฐ๊ตฌ์šฉ (Research)

  • ์ธ์ง€ ๋ชจ๋ธ ์‹œ๋ฎฌ๋ ˆ์ด์…˜
  • ๊ธฐ์–ต-๊ฐ์ •-์˜์‚ฌ๊ฒฐ์ • ๋™์—ญํ•™ ์—ฐ๊ตฌ
  • ๋‡Œ ์งˆํ™˜ ๋ฉ”์ปค๋‹ˆ์ฆ˜ ํƒ๊ตฌ (PTSD, ADHD ๋“ฑ)

๐Ÿญ ์‚ฐ์—…์šฉ (Industrial)

  • AI ์—์ด์ „ํŠธ ๋ฉ”๋ชจ๋ฆฌ ์„œ๋ธŒ์‹œ์Šคํ…œ
  • RAG ๊ฒ€์ƒ‰ ๊ฒฐ๊ณผ ํ•„ํ„ฐ๋ง/๋žญํ‚น
  • LangChain/LlamaIndex ํ†ตํ•ฉ

๐Ÿ’ผ ์ƒ์—…์šฉ (Commercial)

  • ๊ฐœ์ธํ™”๋œ AI ๋น„์„œ์˜ ๊ธฐ์–ต ๋ ˆ์ด์–ด
  • ๊ฒŒ์ž„ NPC ํ–‰๋™ ์—”์ง„
  • ๊ต์œก์šฉ ์‹œ๋ฎฌ๋ ˆ์ดํ„ฐ

๐Ÿ”— ์„ค๊ณ„ ์ฒ ํ•™

Edge AI First

โœ… ๊ฒฝ๋Ÿ‰ ์•Œ๊ณ ๋ฆฌ์ฆ˜ (NumPy ์™ธ ํ•„์ˆ˜ ์˜์กด์„ฑ ์—†์Œ)
โœ… ๋ชจ๋“ˆ๋ณ„ ๋…๋ฆฝ ์‹คํ–‰ ๊ฐ€๋Šฅ
โœ… ํด๋ผ์šฐ๋“œ ์˜์กด์„ฑ ์—†์Œ
โœ… ํ™•์žฅ ๊ฐ€๋Šฅํ•œ ๊ตฌ์กฐ

๋ชจ๋“ˆ ์กฐํ•ฉ

# 1๊ฐœ๋งŒ ์‚ฌ์šฉ
from memoryrank import MemoryRankEngine

# ์กฐํ•ฉํ•ด์„œ ์‚ฌ์šฉ
from cognitive_kernel import CognitiveKernel

# ์ง์ ‘ ํ™•์žฅ
class MyBrain(CognitiveKernel):
    def custom_recall(self): ...

๐Ÿš€ Quick Start

git clone https://github.com/qquartsco-svg/Cognitive_Kernel.git
cd Cognitive_Kernel
pip install numpy

# ์žฅ๊ธฐ ๊ธฐ์–ต ํ…Œ์ŠคํŠธ
python3 cognitive_kernel.py

# 7๊ฐœ ์—”์ง„ ํ†ตํ•ฉ ์‹œ๋ฎฌ๋ ˆ์ด์…˜
python3 examples/full_brain_simulation.py

# 4๊ฐœ ํ•ต์‹ฌ ํŒŒ์ดํ”„๋ผ์ธ
python3 examples/integrated_pipeline.py

๐Ÿ“š ๋ฌธ์„œ

๋ฌธ์„œ ์„ค๋ช…
LONG_TERM_MEMORY.md ์žฅ๊ธฐ ๊ธฐ์–ต ๊ธฐ์ˆ  ๋ฌธ์„œ
API_REFERENCE.md API ๋ ˆํผ๋Ÿฐ์Šค
ARCHITECTURE.md ์ด๋ก ์  ๊ธฐ๋ฐ˜, ์ˆ˜์‹, ์ฐธ๊ณ  ๋ฌธํ—Œ
TEST_RESULTS.md ์ „์ฒด ํ…Œ์ŠคํŠธ ๊ฒฐ๊ณผ
VERIFICATION_STATUS.md ์ด๋ก  โ†” ์ฝ”๋“œ ์ผ์น˜ ๊ฒ€์ฆ

๐Ÿ” PHAM Blockchain Signature

๋ชจ๋“  ํ•ต์‹ฌ ๋ชจ๋“ˆ์€ PHAM (Proof of Honest Authorship & Merit) ๋ธ”๋ก์ฒด์ธ์œผ๋กœ ์„œ๋ช…:

๋ชจ๋“ˆ ์„œ๋ช… ๋“ฑ๊ธ‰
cognitive_kernel.py โœ… A_HIGH (0.9998)
MemoryRank โœ… ์„œ๋ช…
Panorama โœ… ์„œ๋ช…
PFC โœ… ์„œ๋ช…

๐Ÿ“„ License

MIT License โ€” ์ž์œ ๋กญ๊ฒŒ ์‚ฌ์šฉ, ์ˆ˜์ •, ๋ฐฐํฌ ๊ฐ€๋Šฅ


๐Ÿ‘ค Author

GNJz (Qquarts) โ€” @qquartsco-svg



English Version

๐Ÿ‡ฐ๐Ÿ‡ท ํ•œ๊ตญ์–ด | ๐Ÿ‡บ๐Ÿ‡ธ English

Minimal, verifiable implementation of persistent long-term memory for AI agents.

A modular cognitive framework combining Temporal Encoding, Importance Ranking, and Decision Impact.


๐ŸŽฏ Why Now?

Modern LLM agents lack structured long-term memory and executive control.

Cognitive Kernel provides drop-in cognitive subsystems to address this gap.

โš ๏ธ Research and experimentation tool.
   NOT a complete model of the brain, nor a clinical diagnostic tool.

๐Ÿ“Œ This project does not claim biological equivalence to human memory.
   It provides a computer-science definition of long-term memory:
   persistent, structured, recallable, and decision-impacting.

โญ Core Feature: Long-term Memory in 3 Lines

from cognitive_kernel import CognitiveKernel

with CognitiveKernel("my_brain") as kernel:
    kernel.remember("meeting", {"topic": "project"}, importance=0.9)
    memories = kernel.recall(k=5)           # PageRank-based importance recall
    decision = kernel.decide(["rest", "work"])  # Softmax decision-making
# Auto-saved โ†’ Memory persists after process termination

โœ… This gives you:

Feature Description Algorithm
remember() Store memory (long-term) Timeline storage + auto-persistence
recall() Recall important memories Google PageRank
decide() Decision making Softmax Utility

โ†’ Long-term Memory Details


๐Ÿ“ Core Formulas

1. Memory Importance (MemoryRank)

Personalized PageRank algorithm:

$$ \mathbf{r}^{(t+1)} = \alpha \cdot M \cdot \mathbf{r}^{(t)} + (1-\alpha) \cdot \mathbf{v} $$

  • $\mathbf{r}$: Memory importance vector
  • $M$: Memory transition matrix (column-normalized)
  • $\alpha$: Damping factor (default: 0.85)
  • $\mathbf{v}$: Personalization vector (recency, emotion, frequency weights)

2. Temporal Decay (Panorama)

Exponential decay function:

$$ S(t) = S_0 \cdot e^{-\lambda \cdot \Delta t}, \quad \lambda = \frac{\ln 2}{t_{1/2}} $$

  • $S(t)$: Importance at time $t$
  • $t_{1/2}$: Half-life (default: 3600s = 1 hour)

3. Decision Making (PFC)

Softmax selection probability:

$$ P(a_i) = \frac{e^{U(a_i) / T}}{\sum_j e^{U(a_j) / T}} $$

  • $U(a)$: Utility of action $a$ = expected reward - cost - risk
  • $T$: Temperature (exploration vs exploitation balance)

โ†’ Theoretical Foundation


๐Ÿ’พ What is Long-term Memory?

Computer Science Definition

Persistence: Data survives process termination

Cognitive Kernel Implementation

Session A (Process 1)          Session B (Process 2)
โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€         โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€
kernel.remember(...)  โ†’       File saved
        โ†“                          โ†“
Process terminates            CognitiveKernel("my_brain")
                                   โ†“
                              Auto-load โ†’ Memory recovered!

Storage Structure

.cognitive_kernel/my_brain/
โ”œโ”€โ”€ panorama.json      # Timeline events (memory data)
โ”œโ”€โ”€ memoryrank.json    # Importance graph
โ”œโ”€โ”€ edges.json         # Memory connections
โ”œโ”€โ”€ q_values.json      # Habit learning (Q-Learning)
โ””โ”€โ”€ meta.json          # Session metadata

โ†’ Long-term Memory Technical Docs


๐Ÿงช Test Results

Long-term Memory Proof

# Run test
cd /Users/jazzin/Desktop/00_BRAIN/Cognitive_Kernel
python3 cognitive_kernel.py

Result:

๐Ÿ“ฆ Session: test_session
๐Ÿ“ Memories saved: 3
๐Ÿ” Recall (Top 3): idea(0.349), conversation(0.333), meeting(0.318)
๐ŸŽฏ Decision: rest (utility: 0.250)
โœ… Auto-saved!

๐Ÿ”„ Session recovery test...
   Recovered events: 3 โ† Persists after process termination!

7-Engine Integration Simulation

Scenario Stress Max Hyperarousal Efficiency Alerts
Normal Day 0.44 1 0.71 1
PTSD 0.80 3 0.61 5

โ†’ Full Test Results


๐Ÿ“ฆ All Modules

Module Role Core Algorithm Persistence
MemoryRank Memory importance PageRank โœ… JSON/NPZ
Panorama Timeline memory Exponential Decay โœ… JSON/SQLite
PFC Decision making Softmax Utility
BasalGanglia Habit learning TD-Learning โœ… Q-values
Amygdala Emotion/Threat Rescorla-Wagner
Hypothalamus Energy/Stress HPA Dynamics
Thalamus Input filtering Salience Gating

๐Ÿ”ง Use Cases

๐Ÿ”ฌ Research

  • Cognitive model simulation
  • Memory-emotion-decision dynamics research
  • Brain disorder mechanism exploration (PTSD, ADHD, etc.)

๐Ÿญ Industrial

  • AI agent memory subsystem
  • RAG result filtering/ranking
  • LangChain/LlamaIndex integration

๐Ÿ’ผ Commercial

  • Personalized AI assistant memory layer
  • Game NPC behavior engine
  • Educational simulators

๐Ÿ”— Design Philosophy

Edge AI First

โœ… Lightweight algorithms (only NumPy dependency)
โœ… Each module runs independently
โœ… No cloud dependency
โœ… Extensible structure

Module Composition

# Use one
from memoryrank import MemoryRankEngine

# Combine
from cognitive_kernel import CognitiveKernel

# Extend
class MyBrain(CognitiveKernel):
    def custom_recall(self): ...

๐Ÿš€ Quick Start

git clone https://github.com/qquartsco-svg/Cognitive_Kernel.git
cd Cognitive_Kernel
pip install numpy

# Long-term memory test
python3 cognitive_kernel.py

# 7-engine simulation
python3 examples/full_brain_simulation.py

# 4-engine pipeline
python3 examples/integrated_pipeline.py

๐Ÿ“š Documentation

Document Description
LONG_TERM_MEMORY.md Long-term memory technical docs
API_REFERENCE.md API Reference
ARCHITECTURE.md Theoretical foundation, formulas, references
TEST_RESULTS.md Full test results
VERIFICATION_STATUS.md Theory โ†” Code verification

๐Ÿ” PHAM Blockchain Signature

All core modules signed with PHAM (Proof of Honest Authorship & Merit) blockchain:

Module Signed Grade
cognitive_kernel.py โœ… A_HIGH (0.9998)
MemoryRank โœ… Signature
Panorama โœ… Signature
PFC โœ… Signature

๐Ÿ“„ License

MIT License โ€” Free to use, modify, and distribute


๐Ÿ‘ค Author

GNJz (Qquarts) โ€” @qquartsco-svg


๐Ÿค Contributing

Contributions welcome! Please open an issue or submit a Pull Request.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

cognitive_kernel-2.0.0.tar.gz (99.9 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

cognitive_kernel-2.0.0-py3-none-any.whl (92.2 kB view details)

Uploaded Python 3

File details

Details for the file cognitive_kernel-2.0.0.tar.gz.

File metadata

  • Download URL: cognitive_kernel-2.0.0.tar.gz
  • Upload date:
  • Size: 99.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.5

File hashes

Hashes for cognitive_kernel-2.0.0.tar.gz
Algorithm Hash digest
SHA256 74d970a49a8a04f68286cf51fa6f9015cd400c6f8198763c73dc2cbe52c06c70
MD5 c3653b206ed956892d8b4c0198ab756b
BLAKE2b-256 c449ff14efe2bd900e9bb8b561eae657f150de155ef2a0d06648438387042d55

See more details on using hashes here.

File details

Details for the file cognitive_kernel-2.0.0-py3-none-any.whl.

File metadata

File hashes

Hashes for cognitive_kernel-2.0.0-py3-none-any.whl
Algorithm Hash digest
SHA256 e32c278fbe6fb39dba1a7da08d838e9b066be858421312a302774f0da3a605b4
MD5 3a96c569a4648a249b82f6c75882bc04
BLAKE2b-256 5d5c636dc759258dae40977e8038930ab755100bf2668a89d61f87aa575b9b1a

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page