1
KMP (Kernel Memory Protocol) — temporal, multidimensional, auditable AI agent memory.
Agent tooling — page 29
Frameworks, routers and utilities that use Jev to choose tools or branches inside a larger agent system.
1,206 active projects in this collection. All collections →
1
Read-mostly aggregation dashboard for a dev-project portfolio — spend and triage across repos, plugins and vendor APIs. Cloudflare Workers + D1.
The data pipeline behind LinklyAI/best-skills — a daily, cross-ecosystem ranking of AI agent skills
Monorepo of pi extensions: Z.AI web search / vision / ZRead MCP bridges, provider quota footers, and UX tweaks.
create-your-router typescript framework powering dari.dev
Deterministic Rust memory and reliability kernel for AI agents — provenance-bearing memory, contradiction detection, bounded recall, commitments, decision controls.
1
Persistent engineering context and memory for AI coding agents, exposed through MCP.
stuff i use for codex
In-process authorization and tamper-evident audit for Flue agent tools
1
US & EU Job Market Visualizer — Karpathy-style BLS treemaps + ESCO occupations/skills/competences
1
UniLM.jl: A Julian, type-safe interface to LLM providers via the OpenAI-compatible API standard. Supports OpenAI, Azure, Gemini, Mistral, Ollama, vLLM, and any compatible provider, covering Chat Completions, Responses API, Embeddings, Image Generation, and MCP.
No project description available.
Jev (TypeSafe)-backed decision layer for Orca Lab: judges what agents are about to run, and stays out of the way otherwise.
0
Grade an AI agent's job with TypeSafe's Jev: did it do the work as the task laid it out? Facts first, Jev on your own key, a receipt, and optional on-chain records.
fast-jev-compaction for pi and opencode: prune stale tool calls with TypeSafe's Jev instead of summarizing context. Port of tamaratran/fast-jev-compaction.
0
zsh plugin for combining jev with fzf
0
Get coding agents to write Jev questions that work the first time: rules measured on 57 labelled suites.
Jev MCP server: use TypeSafe Jev in Claude & ChatGPT. Yes/no, classification and scoring with probabilities, hosted or self-hosted.
Jev judges every review and return, Elasticsearch aggregates the judgments, and a leashed Claude Code agent turns them into proposed catalog fixes that a person approves.
Model routing for OpenCode powered by the JEV
0
System-1 decision models (Jev/Laya/Kev-class) as the governance layer for an LLM agent context lifecycle: growing association graph over session segments, relevance-gated recall with Trace-as-State ordering, and plan pre-ranking — measured in solve rate, cache hit/miss tokens, cost and latency. DSH plugin + harness-agnostic proxy.
No project description available.
0
Universal AI Agent Control Plane: LLM agents (Claude Code, Codex, Gemini, OpenCode) do the work, Jev judges typed decisions, executed checks provide the evidence.
0
Anchor: ground truth for Pi agents, backed by MongoDB Atlas verified state