Repository intelligence

dadbodgeoff/drift

GitHub

Drift brings persistent codebase intelligence to your development workflow, acting as a memory layer for AI coding assistants. It detects patterns and conventions across your codebase, remembers architectural decisions across sessions, and integrates seamlessly with any IDE through the Model Context Protocol. Whether you're working solo or collaborating with AI pair programmers, Drift ensures your AI tools understand the "why" behind your code—not just the "what."

CLOUDM0N decision
REVIEW BEFORE ADOPTION
Trust REVIEW · 80/100
Good fit if

Teams whose requirements match this repository’s core capability.

Watch out for

Review deployment and security evidence before production adoption.

Practical intelligence

What matters before you adopt it

Best for
Teams whose requirements match this repository’s core capability.
Main trade-offs
Review deployment and security evidence before production adoption.
Trust & CVEs

Security evidence without the noise

Trust remains a decision signal; CVEs and scanner evidence explain what is driving the risk.

Security findings
2
CLOUDM0N scanner findings
Critical
0
High
0
Medium
2
Low
0
View trust evidence & security findings
Why this score
No trust rationale was stored for this scan.
CLOUDM0N findings
MEDIUM
Dynamic code execution pattern detected. 5 sample match(es) found.
MEDIUM
The project can spawn operating-system processes; review command construction and input handling. 5 sample match(es) found.
Architecture from code20 modules · 7 edges
Structural evidence

Modules and dependency edges extracted from repository code. This is code evidence, not README inference.

Code files
713
Modules
20
Dependency edges
7
Core modules
packages/adapters
2 files
packages/cli
171 files
packages/core
core utilities
42 files
packages/engine-contract
5 files
packages/factgraph
3 files
packages/mcp
9 files
packages/query
32 files
packages/storage
12 files
packages/vocabulary
1 files
scripts
55 files
vocabulary
1 files
Dependency flow
packages/clipackages/core
packages/mcppackages/cli
scriptsvocabulary
Detected languages
TypeScript · JavaScript · Rust · Shell · Python
Detected frameworks
Vitest
Architecture evidence details
flowchart TD
    %% drift — high-level architecture (DRAFT, refine me)
    n0["docs · documentation · 5 files"]
    n1["packages/adapters · 2 files"]
    n2["packages/cli · 171 files"]
    n3["packages/core · core utilities · 42 files"]
    n4["packages/engine-contract · 5 files"]
    n5["packages/factgraph · 3 files"]
    n6["packages/mcp · 9 files"]
    n7["packages/query · 32 files"]
    n8["packages/storage · 12 files"]
    n9["packages/vocabulary · 1 file"]
    n10["scripts · scripts · 55 files"]
    n11["test · tests · 375 files"]
    n12["vocabulary · 1 file"]
    n2 --> n3
    n6 --> n2
    n10 --> n12
    n11 --> n2
    n11 --> n3
    n11 --> n6
    n11 --> n8
    class n3 core
    class n0 docs
    class n10 infra
    class n11 test
    classDef core fill:#e15759,color:#ffffff,stroke:#b04547
    classDef docs fill:#9d7660,color:#ffffff,stroke:#7c5d4c
    classDef infra fill:#b35c00,color:#ffffff,stroke:#8f4a00
    classDef test fill:#499894,color:#ffffff,stroke:#397975
Agent handoff
Use with any agent
JSON API
Alternatives

Nearby repositories worth comparing before adoption.

Compare top options →
posthog
PostHog/posthog
23
Fit

:hedgehog: PostHog is the leading platform for building self-driving products. Our developer tools – AI observability, analytics, session replay, flags, experiments, error tracking, logs, and more – capture all the context agents need to diagnose problems, uncover opportunities, and ship fixes. Steer it all from Slack, web, desktop, or the MCP.

Trust FAIL · 0
Compare →
SocratiCode
giancarloerra/SocratiCode
59
Fit

Tired of AI tools hallucinating about your codebase or burning through your API quota? SocratiCode flips the script with local-first, privacy-safe codebase intelligence that handles 40M+ lines of code without breaking a sweat. It delivers hybrid semantic search, dependency graphs, and impact analysis that devs actually need — all while cutting tokens by 61% and calls by 84%. Whether you're on Claude, Gemini, or rolling your own setup, this tool speaks your language.

Trust REVIEW · 55
Compare →