Skip to content
View tobs-code's full-sized avatar

Block or report tobs-code

Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse

Pinned Loading

  1. sieveon-memory-mcp sieveon-memory-mcp Public

    A workload-adaptive agent memory system combining event logs, knowledge graphs, and vector embeddings

    Python 1

  2. ghostAudit ghostAudit Public

    Steganographic audit logging inside SQLite — hides forensic data in ordinary user-data fields with RAID-6 erasure coding, adaptive Reed-Solomon ECC, and rollback detection. Research project.

    Python 1

  3. llm-control-circuits llm-control-circuits Public

    Mechanistic interpretability experiments on political control circuits, refusal behavior, concept steering, and late-decoder interactions in open LLMs.

    Python 2

  4. prompts prompts Public

    Prompt engineering for people who don't trust vibes -- Strict tools for critical cases, flexible ones for creative ones (not in this repo). Not intended for creative stuff.

    8 2

  5. policy-gate policy-gate Public

    Deterministic allowlist-first policy gate for LLM applications, agents, and AI gateways.

    Rust 1

  6. SoftPrompt-IR SoftPrompt-IR Public

    SoftPrompt-IR is a low-level symbolic annotation layer for LLM prompts, making intent strength, direction, and priority explicit. It is not a DSL or framework, but a minimal, composable way to redu…

    11