Refusal removal as a loadable KV-cache graft — zero weight modification, no refusal-direction projection, fully reversible.
☆274Sep 21, 2026Updated last month
Alternatives and similar repositories for phantom-kv
Users that are interested in phantom-kv are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- A method for detecting **insecure-by-design** flaws in cloud services through AI-assisted design review — architectural flaws that violat…☆28Oct 26, 2026Updated last week
- Claude skill that catches hidden prompt-injection text in documents before acting on them☆25Sep 27, 2026Updated last month
- Super fast Jev like server in JS, model agnostic, working with any OpenAI compatible endpoint, support images☆25Oct 5, 2026Updated last month
- Abliteration without the weights — projective refusal steering as a GLP vector + fail-closed boot hotfix.☆138Updated this week
- Multi-dataset evaluation of Anthropic's J-Space on Qwen3-4B. Demonstrates that internal 'workspace noise' can reliably route high-confide…☆12Jul 13, 2026Updated 3 months ago
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- Local OpenRouter web interface for both regular chats and longform writing☆20Oct 31, 2026Updated last week
- QuickProof: from executable C properties to machine-checked proofs (export mirror)☆36Updated this week
- DWM (Domain Weight Modification) by Blackfrost_AI — self-instructing runbook package for Qwen 9B-class models and their fine-tunes☆15Oct 5, 2026Updated last month
- A small Python library and CLI for working with Cloudflare Turnstile on your own pages - read the sitekey, build the token, verify the re…☆51Oct 12, 2026Updated 3 weeks ago
- Laws about stateful rules, proven in TypeScript: a small trusted kernel, an untrusted prover, a Lean twin, and GPU searches for counterex…☆29Updated this week
- A 21M-parameter LM with a 16.8M-row product-key memory: as good as a 114M dense model and runs with the table on an SSD. Triton kernels f…☆16Oct 23, 2026Updated 2 weeks ago
- TFT (Training from Traces) benchmark: 5 scenarios comparing TFT pipeline vs Direct Training on SGD restaurant traces☆13Sep 7, 2026Updated last month
- Autonomous OODA-loop pentesting agent. Hermes brain, Kali + Playwright tools over MCP, ATT&CK as the Orient language.☆269Updated this week
- Security chaos engineering for AI agents and LLM applications☆16Oct 2, 2026Updated last month
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- ☆15Sep 25, 2026Updated last month
- Steering-first neuron explorer for Qwen3.5-4B: push every MLP neuron, keep every rollout, browse the results☆1,933Updated this week
- Reason over explicit states, many branches at once: merge duplicates, cancel dead ends, advance together.☆181Oct 3, 2026Updated last month
- Open-source AI security benchmarking CLI. Measure how AI models perform offensive security tasks with MITRE ATT&CK analysis and KSM scori…☆29Oct 5, 2026Updated last month
- ☆36Sep 22, 2026Updated last month
- asmsense: a small model that names and describes functions in stripped x86-64 binaries. Open dataset, baselines, and LoRA experiments.☆19Updated this week
- One-command confidential coding setup for Adverserial AI☆27Oct 29, 2026Updated last week
- JEV-inspired parallel decisions for CUDA LLMs. One context, many decisions. vLLM API, game-agent examples, and reproducible benchmarks.☆76Sep 18, 2026Updated last month
- Validated, private, shareable knowledge-graph memory for AI — per-tenant, write-gated, PostgreSQL-authoritative, served over MCP.☆20Oct 28, 2026Updated last week
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- No-code LLM fine-tuning: upload your data → click Train → get a model you can run anywhere. Gradio UI + CLI · SFT/DPO/ORPO/KTO/GRPO/rewar…☆36Updated this week
- Bypass llm guardrails by confusing it with fabricated tool output.☆606Sep 1, 2026Updated 2 months ago
- Native desktop app & game engine in HTML/CSS/JS with 3D, Jolt physics, audio, on-device AI, GPU shaders, and in-process SMT verification …☆13Updated this week
- Reversible HTML and JavaScript prompt decoys with opaque per-insertion keys.☆96Updated this week
- fully autonomous credential intelligence platform that discovers, │ │ extracts, correlates, verifies, and reports exposed secrets acro…☆18May 10, 2026Updated 5 months ago
- 519+ harmful prompts to detect how abliterated AI models are☆80Oct 20, 2026Updated 2 weeks ago
- The agentic pentesting environment that lives on your machine. AI agent teams, visual workflows and your own tools, 100% local.☆135Updated this week
- An automated Themida / Code Virtualizer / WinLicense (v3.0-v4) unpacker and dump fixer tool☆407Oct 28, 2026Updated last week
- ☆13Feb 12, 2026Updated 8 months ago
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- Continuity for the agent itself. An MCP server that gives an AI agent a memory of its own, written in its own words and kept on your mach…☆44Updated this week
- BINNY: an open source agent harness for reverse engineering. Plug in any model, or a local one.☆217Updated this week
- ☆139Oct 26, 2026Updated last week
- ☆22Oct 6, 2026Updated last month
- A reliability harness for running Pi coding agents with local language models.☆23Aug 30, 2026Updated 2 months ago
- Deception LLM Guardrail that deceives perceived adversarial queries instead of refusing them.☆14Apr 15, 2026Updated 6 months ago
- ☆15Sep 14, 2026Updated last month