Security●●●Banger
MVAR – Deterministic sink enforcement for AI agent
IFC + capabilities block prompt injection at execution sinks, not input filters—40yr research applied.
Big BrainWizardry
ShawnC21
113mo ago
Back to browse
GitHub Repository
A Python framework for modular, self-contained skill management for machines.
51 starsPython
A deterministic middleware to compress LLM prompts by 50-80%
by rosspeili·Mar 21, 2026·3 points·0 comments
AI Analysis
●●SolidBig BrainNiche Gem
Deterministic prompt compression cuts tokens 50-80% without extra model calls.
Strengths
- •Offline heuristic compression avoids additional LLM calls and reduces inference costs
- •Modular skill registry standardizes agent capabilities across Gemini, Claude, and GPT
Weaknesses
- •Only 11 stars suggests limited adoption and untested community momentum
- •Broader framework vision remains unproven at scale beyond prompt rewriter
Category
Target Audience
AI/LLM developers building agentic systems
Similar To
LangChain · LlamaIndex · Haystack
Post Description
Hi HN,
I’m working on Skillware, an open-source framework that treats AI capabilities as installable, self-contained modules.
I just added a "Prompt Token Rewriter" skill. It’s an offline heuristic middleware that strips conversational filler and redundant context from long agentic loops before they hit the LLM. It saves significant token costs and inference time, and it's 100% deterministic (no extra model calls).
We're building a registry of "Agentic Know-How" (Logic + Cognition + Governance). If you have a specialized tool for LLMs or want to see what a "standard" skill looks like, I'd love your feedback or a PR:
Similar Projects
AI/ML●●Solid
Assembly Language for Agents
This repo turns agent loops into tiny, explicit instructions (LF, LI, APP, INF, INT, BGT, OUT) so you can compose reasoning as discrete micro-prompts instead of one huge monolith. The example VIBE_CONTROLLER shows concrete ops for cognition, safety checks and branching — a neat way to formalize ReAct-style loops. It’s a clever, researchy DSL with a Rust interpreter, but it’s early-stage and sits in a crowded space of agent frameworks (needs runtime benchmarks, integrations and real-world demos to move beyond an interesting experiment).
Big BrainNiche Gem
vanilla-latte
224mo ago
AI/ML●Mid
The Agent Skills Standard – A modular approach to LLM context
Modular context folders beat monolithic prompts for scaling AI agent instructions.
Big Brain
muhammad-shafat
303mo ago
Developer Tools●●Solid
Orangensaft – A mini Python-like language with LLM eval in lang runtime
Treats model calls as first-class runtime constructs using $..$ blocks with declared-type enforcement, which makes it unusually ergonomic to intermix deterministic code and LLM-powered operations. The Polars-backed dataframe injection that emits structured JSON summaries instead of raw table dumps is a clever, practical touch for token efficiency; neat sandbox for language designers, but explicitly a hobby/toy project rather than something to deploy.
Bold BetWizardry
jargnar
104mo ago
Developer Tools●●Solid
Argmin AI, system level LLM cost optimization for agents and RAG
LLM cost optimizer, but Anthropic's batch API and local quantization solve this cheaper.
Solve My ProblemBig Brain
konyrevdmitriy
203mo ago
AI/ML●●●Banger
ARISE – Agents that create their own tools at runtime when they fail
Agents synthesize and test their own tools when they fail, not just chain APIs.
Big BrainZero to One
abekek
303mo ago