04 · 117 projects
Jev for context & memory
Agents drown in their own context. These projects use Jev to decide what to keep, what to drop and when a loop is actually finished.
What Jev decides: Keep or discard a tool result, or answer whether a stopping condition is met.
Projects, newest first
Context & memoryfast-compact/fc for Claude Code: TypeSafe Jev picks which old tool outputs are still needed and keeps them whole, other outputs are cut to head/tail with every…GitHub · ★ 6 · NodarDavituri
Context & memorypi-context-decisionsPi extension that uses decision models (TypeSafe Jev, OpenRouter decision models, OpenAI Luna) to filter which skill advertisements enter context for…GitHub · championswimmer
Context & memoryOpen Memory (pi)Local-first SQLite memory for Pi agents with hybrid retrieval and a hard token budget; an optional TypeSafe Jev judge decides which sentences are…GitHub · ★ 1 · codersdfs
Context & memoryJev Gate (royalskynet)MCP server and Claude Code/Codex plugin that uses Jev to keep only the parts of logs and tool output that matter, shorten long conversations, and…GitHub · royalskynet
Context & memoryOpenVikingVolcengine's agent context database that unifies memory, knowledge RAG and skills under a viking:// virtual filesystem; it ships a Jev rerank client…GitHub · ★ 40k
Context & memoryMinutesAn MIT-licensed, local-first conversation memory app that transcribes meetings, calls and voice memos on-device into Markdown you own.GitHub · ★ 1.5k
Context & memoryJIT-JEV Context OSJIT-JEV Context OS: epistemic context runtime plus a System 1 Jev decision gate for autonomous coding agents with tool access.GitHub · ★ 9 · wojciechwiesner
Context & memoryopencode-jev-compactionOpenCode plugin that compacts sessions by pruning with Jev instead of summarizing.GitHub · ★ 1 · radqnico
Context & memoryLossless CompactionClaude Code plugin that compacts conversations by moving old tool results to local files instead of summarizing them, leaving a ticket line in their…GitHub
Context & memoryJev Agent Kit (cloud-f1)Claude Code plugin that shortens long Bash output before it reaches the model, using a local rules engine with an optional Jev relevance pass; the…GitHub · cloud-f1
Context & memorypaseo-jev-compactionSeparate Paseo provider for Codex that tries Jev history compaction first on manual and context-limit compaction, falling back to Codex when Jev…GitHub · hakilee
Context & memoryJev Lucid MemoryResearch prototype of wake–sleep memory for AI agents: an LLM drafts lessons from task records, a decision model (TypeSafe Jev via the official SDK…GitHub · ★ 2 · JayYun98Context & memorydotfilesFlags what you might miss in an agent's output, at close to no cost.GitHub · Nate Berkopec
Context & memorydefragResearch tool for telling a coding agent's user when compacting is safe — at the quiet point between tasks, not when the context is nearly full: it…GitHub · jaylamping
Context & memorylaya-compactionPort of the listed fast-jev-compaction that swaps TypeSafe Jev for Laya, the open Jev-compatible decision model: a Claude Code plugin and npm library…GitHub · bussolabs
Context & memoryfast-jev-compaction-openrouterFork of tamaratran/fast-jev-compaction: Jev via OpenRouter with zero data retention (zdr, data_collection: deny).GitHub · ★ 2 · ingebyd
Context & memorycontextleleoCarry a coding agent's session to the next agent (Claude Code → Antigravity and others) trimmed to what the next task needs: TypeSafe Jev scores what…GitHub · Adityakk9031
Context & memoryjev-tokensaverClaude Code and Cowork pre-reader: a local jev CLI, MCP server and skill that let TypeSafe Jev read long test logs, big files and candidate-file…GitHub · Dinesh-SunnyContext & memoryHow I Used Claude Code Mods to Build a 3600X Cheaper Memory Harnessshawn’s step-by-step guide: Claude Code Mods plus Jev make a custom memory harness for Claude Code.X postContext & memoryAskHIGJev picks which Apple HIG guides go into the agent's context.X post · NatashaTheRobot
Context & memorydsh-plugin-jev-compactionDeepSeek Harness plugin: TypeSafe Jev scores messages for relevance-based compaction (pins constraints/tracebacks; falls back to age-based on…GitHub · ★ 1 · YYTbit
Context & memoryjevmem (illescasDaniel)Agent long-term memory via TypeSafe Jev typed decisions (MCP, Claude Code hooks, CLI, SQLite)—no generative LLM in the memory loop (MIT; distinct…GitHub · ★ 1 · illescasDaniel
Context & memoryLongjevPython wrapper giving Jev long-input support: scores chunks per question, keeps the best within a token budget, marks omissions, and checks…GitHub · ★ 1 · avshalomd
Context & memoryDuet AgentAgent harness for work that outlives one chat, with resumable turns, routed state machines, and observational memory across sessions and processes.GitHub · ★ 49 · dzhng
Context & memoryTocketFile-first project notebook where many agents share context in .context/ files while Jev only judges the next step and records it as JSON.GitHub · ★ 38 · pedrocivita
Context & memoryAstraSelf-hosted agent runtime that adds an optional Jev judgment layer to memory filtering, lesson dismissal, request classification, and skill…GitHub · ★ 34 · matrixorigin
Context & memoryjev-compaction-plusClaude Code compaction via TypeSafe Jev keep/drop; retained text stays verbatim and dropped tool outputs move to a drawer file (fork of…GitHub · ★ 26 · cth9191
Context & memoryHafiza OSTurkish-language local-first memory starter that keeps preferences, decisions, jobs, and sources in your own Markdown vault and points Claude Code,…GitHub · ★ 21 · fornhere
Context & memoryPi DcpPi extension that trims wasted context before each model call by deduplicating repeated tool results, stripping failed payload args, and letting the…GitHub · ★ 17 · Davidcreador
Context & memoryTiermemTiered agent memory keeping compact summaries with source links over searchable raw history, where a router decides per query whether notes suffice…GitHub · ★ 14 · FreedomIntelligence
Context & memoryJev by ExampleTen runnable JavaScript lessons on agent decisions between steps—memory conflicts, evidence gaps, tool-result completion, retries, context budget,…GitHub · ★ 3 · ReallyArtificialContext & memoryJevkeepA Codex plugin that asks Jev which conversation passages still matter, lets Codex compact normally, then restores the selected excerpts verbatim…GitHub · ★ 1 · hatt-io
Context & memoryOmp StatifyAn Oh-my-pi extension that asks Jev which parts of large tool results are worth keeping before they enter the main model's context, and can also trim…GitHub · ★ 1 · d3d0n
Context & memoryclaude-jev-advisorUnofficial Claude Code command hooks using TypeSafe Jev: a context helper that suggests /compact or /clear at natural stopping points, and (on…GitHub · delt96
Context & memoryTotal Agent MemoryAn MCP memory server for coding agents: decisions, fixes and session summaries live in a local SQLite store, and recall fuses BM25, locally computed…GitHub · ★ 73 · vbcherepanov
Context & memoryfast-jev-compaction-opencodeopencode plugin for verbatim session compaction via probabilistic keep/drop judgments (based on tamaratran/fast-jev-compaction); default judge is a…GitHub · dex-community
Context & memoryhermes-jev-lesson-gateHermes Agent plugin: TypeSafe Jev (OpenRouter Decisions) judges when memory/skill background review should run—replacing a fixed every-N-turns clock.GitHub · VBS2004
Context & memorymnemon-memory-agentLong-term memory for AI agents: keep raw records and use TypeSafe Jev System One to judge what to retain and surface.GitHub · ★ 4 · Grivn
Context & memoryCodex-JevVS Code Codex plugin that shortens noisy tool results with Jev-gated evidence selection before Codex reads themGitHub · ★ 2 · PhilippElhaus
Context & memoryfast-jev-opencode (roshan-shaik-ml)Verbatim OpenCode context prune powered by TypeSafe Jev—history and UI stay untouched.GitHub · roshan-shaik-ml
Context & memoryjev-pi-token-reductionPi coding-agent extension: TypeSafe Jev trims tool-output chunks before the model sees them (~15% cost on held-out reads).GitHub · auschoi96
Context & memoryHearMemoryShared project memory for multi-agent coding (Claude Code, Codex, Cursor): TypeSafe Jev judges claims against recorded evidence (tests, diffs,…GitHub · ★ 3 · ssd1051
Context & memoryjev-compactionContext compaction library (jevctx) where Jev only scores—never rewrites—so retained lines stay original, elided text is recoverable byte-for-byte,…GitHub · ★ 4 · Waxmell114514
Context & memoryjev-skillsClaude Code / Codex plugin: TypeSafe Jev decides which installed skills enter context each turn—always-on skill-list cost drops to zero tokens.GitHub · ★ 3 · eran-broder
Context & memoryopencode-context-prunerContinuous verbatim context pruning for OpenCode, powered by TypeSafe Jev.GitHub · ★ 2 · hoshinodis
Context & memoryjev-filterSemantic filtering for AI agent tools: npm package @apixly/jev-filter (CLI, Python library, MCP server) turns large tool outputs, retrieved records,…GitHub · ★ 1 · apixly-ai
Context & memoryA memory gate for Claude CodeOne question per message: is this worth remembering?X post · Jetwani Avinash
Context & memoryBeacon fixes a coding agent’s memoryJev on the memory decisions in a coding agent.X post · cyrilXBT
Context & memoryHow Jev and Laya help support agents prepare contextBoth models tried on an agent’s context step.X post · edwinfmesa
Context & memoryThe state packet you put in front of JevState is evidence, not a second prompt.X post · morph
Context & memoryheadroomA local-first brain-budget meter for Codex, scored by Laya.GitHub · ★ 5 · llm-learner
Context & memorycairn-jev-labTest what your AI should remember, with Jev deciding admission.GitHub · ★ 4 · Cairn-ink
Context & memoryjevmemShared JEVMEM.md project memory for Claude Code, Cursor, and Codex: TypeSafe Jev decides whether each turn is worth remembering; optional LLM…GitHub · ★ 2 · Avinash-jetwani
Context & memorydsh-context-curatorDSH-native context compaction that keeps text verbatim: scores every tool call and result with Jev, drops only the stale ones, and falls back to DSH…GitHub · ★ 2 · LXBWOW
Context & memoryjev-skill-selectionPre-message hook: use TypeSafe Jev to keep/drop skills and shrink agent context.GitHub · ★ 2 · redreamality
Context & memoryInstant Claude Code compactionJev compacts the context the moment a redeploy makes it stale.X post · WesternCube
Context & memoryJev-MemA paper on System-One-controlled agentic memory.X post · SciFi
Context & memorymemsearchPersistent Markdown-backed memory for coding agents (Claude Code, Codex, DeepSeek Harness, OpenClaw, OpenCode) indexed in Milvus, with optional…GitHub · ★ 2.7k · zilliztech
Context & memoryBeaconAn open-source, local-first memory layer that captures session history across Claude Code, Cursor, Codex, OpenCode, Cline, and 20+ other harnesses,…GitHub · ★ 1.6k · Asymptote-Labs
Context & memoryHippoA local SQLite memory layer for CLI agents with an opt-in Jev reranker that batches Noul judgments over the top 40 recalled memories and falls back…GitHub · ★ 758 · kitfunso
Context & memorySave Token JevA Jev-guided context compaction library for coding agents: instead of summarizing old context, Jev decides which tool calls and results still matter…GitHub · ★ 73 · IAmUnbounded
Context & memoryjevmoryLocal-first coding-agent memory CLI: ingest session transcripts into SQLite with redaction, optionally grade candidates with TypeSafe Jev, and audit…GitHub · ★ 11 · romiluz13
Context & memoryjev_project_contextEvidence-first long-term experiment memory skill for AI coding agents: structured lab-notebook operations with optional TypeSafe Jev semantic triage…GitHub · ★ 9 · poiuyjie
Context & memorydeepseek-harness-jev-pre-compactionA pre-compaction advisor for DeepSeek Harness.GitHub · ★ 5 · wjw66
Context & memoryAlphaOptimizerCodex-oriented tool that keeps large command/tool outputs usable: store the full text locally with limits, and optionally ask TypeSafe Jev which…GitHub · ★ 4 · alpha-tales
Context & memoryhermes-jev-curatorTyped relation governance and safe archive plans.GitHub · ★ 2 · anpicasso
Context & memoryJev-MemSystem-One–controlled agentic memory: TypeSafe Jev steers admission, multi-relational graph linking, and adaptive retrieval over preserved…GitHub · ★ 88 · libingzheren
Context & memorypi-jev-context (Nyarlathoteppppp)Trim long tool outputs for the pi coding agent before they enter context, so prompt-cache prefixes stay intact: comparison-based collapses for…GitHub · ★ 8 · Nyarlathoteppppp
Context & memoryjev-harnessEvery tool result is filtered by Jev before the model reads it.GitHub · ★ 5 · AstroHan
Context & memorydsh-jev-pruneContext compaction for DeepSeek Harness, judged by Jev.GitHub · ★ 3 · yangyu666
Context & memoryPerfectRecallAgent memory where Jev decides what is worth recalling.GitHub · ★ 2 · arslanr-com
Context & memoryjevskillTeach your coding agent to stop burning context.GitHub · ★ 1 · lazniak
Context & memoryLet Jev pick the memories, not the answerCandidates selected for Codex or Claude Code to read.X post · taku_ai_case
Context & memorySimple Jev, reusing the KV cacheShared context cached, only the candidate logits read.X post · vintcessun
Context & memorySkill suggestion against context bloatOn-demand loading for a folder full of custom skills.X post · realfxw
Context & memorySkill suggestion injects one skillJev decides which skill is relevant, so the rest stay out of context.X post · Shweta Bajaj
Context & memoryThe unglamorous Jev jobsPerformance checks after a ship, chat compaction, prioritising work.X post · rakshaa_t
Context & memorycompact-adviserTells you when your session is at a safe point to compact.GitHub · ★ 184 · kunchenguid
Context & memoryjev-recallRetrieve by relevance, not resemblance: filter an AI assistant's memories with TypeSafe's Jev.GitHub · ★ 37 · samdotmak
Context & memoryCheshiJev-powered conversation memory: find past sessions and revisit decisions with original sources.GitHub · ★ 19 · CheshiAI
Context & memorypi-jev (iefnaf)Pi extension suite powered by Jev: selective context compaction and model routing.GitHub · ★ 9 · iefnaf
Context & memorywindows-save-token-jev-setupWindows Codex Skill：通过 npx 或 Git 安装，安全配置 save-token-jev 的 PreCompact/SessionStart Hooks，并提供信任、原生压缩与旧内容隔离验证。GitHub · ★ 4 · 455-dIAO
Context & memorydgui-hypermemDGUI-HyperMem (DeckerGUI HyperMemory) - self-hosted hybrid memory MCP server on Cloudflare Workers with a JEV (Choice/Noul/Score) reasoning layer and…GitHub · ★ 2 · ctaxnagomi
Context & memoryjev-prunerTrims long Bash output with Jev before Claude reads it.GitHub · ★ 146 · tamaratran
Context & memoryinvalidateSemantic TTL for agent memory: each stored fact gets a lease; new evidence is checked against every memory with TypeSafe Jev, then code marks…GitHub · ★ 21 · chopratejas
Context & memoryjev-compactCodex CLI plugin that scores tool calls with TypeSafe Jev before compaction, then re-injects verbatim any critical outputs the built-in summary…GitHub · ★ 8 · fatelei
Context & memoryfast-jev-opencodeOpenCode V2 plugin that scores tool calls/results with TypeSafe Jev and rewrites only the outgoing model request (drop/truncate), fail-open and…GitHub · ★ 6 · nrdz-labs
Context & memoryjevpruneFilter command output for coding agents using a task description.GitHub · ★ 2 · ibrahemid
Context & memoryJev RunwayLocal proxy for Codex that asks TypeSafe Jev which old tool outputs the session still needs and trims the rest before each provider request.GitHub · ★ 2 · IPECTER
Context & memorypi-fast-jev-compaction (KamilPostrozny)Fast JEV compaction extension for pi.GitHub · ★ 2 · KamilPostrozny
Context & memorypi-jev-contextReversible context pruning for Pi, powered by TypeSafe Jev.GitHub · ★ 2 · kevinpita
Context & memoryContext compaction evaluationOkay, everyone wants us to give the unbiased facts.GitHub · Teknium 🪽
Context & memoryFast Jev CompactionDecide which tool interactions to retain.GitHub · ★ 6.8k · tamaratran
Context & memoryjev-rulesJev picks which of your rules apply, so Claude only sees those.GitHub · ★ 49 · Elia Alberti
Context & memoryyoshiA context-pruning proxy for Claude Code and Codex.GitHub · ★ 26 · compozy
Context & memorypi-fast-jev-compactionPi extension: verbatim context compaction with TypeSafe Jev decisions.GitHub · ★ 12 · joelhooks
Context & memoryomp-jev-compactionVerbatim, Jev-scored context reduction for omp: tool calls and results are scored with TypeSafe Jev (or OpenRouter’s Decisions path); low-scoring…GitHub · ★ 9 · jerryfane
Context & memoryfast-dev-compactionCodex plugin: verbatim Jev-guided context restoration around session compaction.GitHub · ★ 6 · leonaaardob
Context & memorypi-jev-context-curatorA context curator for the Pi agent, built on Jev.GitHub · ★ 5 · Shashank-H
Context & memorypi-jev-compactionAutomatic context clearing for Pi, without losing the conversation.GitHub · ★ 4 · nourhelmi
Context & memorycodex-context-dietA Codex plugin where Jev trims bulky tool results.GitHub · ★ 4 · Konstantinos BotonakisContext & memoryThe case against Jev compactionTheo on why per-tool-call filtering is not compaction: lost reasoning, higher cache-write costs and agents stuck in loops.X post · Theo
Context & memoryThe compaction plugin, in SpanishErick on fast-jev-compaction: instead of summarising the context, Jev prunes it, keeping what matters word for word.X post
Context & memoryForemanCheck progress and completion in an agent loop.GitHub · ★ 554 · thruwire
Context & memoryWinnowFilter tool output before it enters context.GitHub · ★ 86 · GhalebDweikat
Context & memoryLimpetCheck stopping conditions against written rules.GitHub · ★ 4 · noplan-inc
Context & memoryInstant compaction for ClaudeJev scores every tool call and drops the ones that no longer matter.X post · Tamara Tran
Context & memoryStop making models relearn the repository.Stop making models relearn the repository.GitHub · ★ 2 · Zerolitter
Context & memoryprebriefI made a thing called Prebrief that keeps my agents up to speed on what I’m doing across sessions.GitHub · blake
Context & memoryEngraphisLocal-first, inspectable memory for coding agents (MCP, code-aware recall, WebUI) with optional advisory Jev decisions via BYOK or managed hosted…GitHub · ★ 175 · Coding-Dev-Tools
Context & memoryZerikai MemoryLocal code-memory MCP server with a TypeSafe Jev semantic judgment layer over retrieved snippets for coding agents.GitHub · ★ 36 · KikeVenContext & memoryFAVA TrailsGit-native, versioned memory for AI agents via MCP (Machine Wisdom AI): drafts are isolated, and since 0.8 the default Trust Gate asks TypeSafe Jev…Site · MachineWisdomAI
Context & memoryhermes-pluginsJev handling part of the hermes compaction, fun little side projectGitHub · TheEpTic
Context & memorynachalnikJev-assisted context compaction in the kamchatka agentGitHub · ljedrzContext & memoryNavigator (qf-studio)Context-engineering plugin for Claude Code (loop mode, research, memories, live /nav pane) whose keyword prompt gates can get an optional typed…Site · qf-studio
Context & memorypromptforce.aiSummary Jev Rerank Experiment for code context The eval: ReadyBase ( - my tool to provide meaningfully viable per turn context to coding agents)…Site · PromptForcePrimeContext & memorySuperLocalMemoryLocal-first, governed memory for AI agents (SQLite, hybrid recall, time-aware facts) with an optional answer check that asks Laya on-device or Jev…Site · qualixarOther use cases
Agents & browsers 299Coding & code review 450Routing & model choice 348Search & RAG 108Data & extraction 98Documents & research 45Safety & guardrails 229Support & inbox 81Marketing, sales & social 120Trading & finance 77Games & real time 256Creative & generative UI 69Home, robots & devices 31Everyday apps 176SDKs & integrations 625Benchmarks & research 682Guides & docs 342