Loading video...

Video Failed to Load

Go Home

Sibyl Memory Plugin. closed beta is opening. one command, any harness. -95.1% on longmemeval. -file-based. -zero vectors. -hierarchical schema. early data is showing a 52% reduction in token usage. bounty board goes live tomorrow. come learn, earn & build.

sibylcap's profile picture

SIBYL

2,090 subscribers

31,059 views • 5 months ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Make Claude Code 10x more powerful. Claude-Mem is a free plugin to persist memory across Claude sessions. It captures tool usage, so you always start where you left off. Endless Mode allows 95% token reduction & 20x more tool use before context exhaustion. 100% open-source.
0:25

Make Claude Code 10x more powerful. Claude-Mem is a free plugin to persist memory across Claude sessions. It captures tool usage, so you always start where you left off. Endless Mode allows 95% token reduction & 20x more tool use before context exhaustion. 100% open-source.

Akshay 🚀

184,914 views • 10 months ago

DotChat is now live in its beta cohort, first come, first served. Available at: Fully anonymous 100 user capacity Zero retention, zero data logging Uncensored frontier model capabilities Fully anonymous user Chat Lounge Build better, with Dot.
0:34

DotChat is now live in its beta cohort, first come, first served. Available at: Fully anonymous 100 user capacity Zero retention, zero data logging Uncensored frontier model capabilities Fully anonymous user Chat Lounge Build better, with Dot.

Dot

11,631 views • 5 months ago

Versus-X Closed Beta is live! 🚀 As of this very minute, the closed beta is live exclusively on Ultra Play against friends, earn tokens by wagering on your gaming skills in a brand new web3 gaming ecosystem. Download the game here: Let the games begin, Rookies!
0:40

Versus-X Closed Beta is live! 🚀 As of this very minute, the closed beta is live exclusively on Ultra Play against friends, earn tokens by wagering on your gaming skills in a brand new web3 gaming ecosystem. Download the game here: Let the games begin, Rookies!

Versus-X

18,276 views • 2 years ago

1️⃣ Connect any wallet, any chain. Discover any token in seconds. 2️⃣ Play & earn. Create or join token powered games. Win, lose, stake, all on-chain. 3️⃣ Trade & check charts live. Real-time data and instant swaps. 4️⃣ Lock tokens, build reputation. Earn credits and share ecosystem rewards. 5️⃣ Leverage Web3 community power to accelerate Web2 growth.
1:12

1️⃣ Connect any wallet, any chain. Discover any token in seconds. 2️⃣ Play & earn. Create or join token powered games. Win, lose, stake, all on-chain. 3️⃣ Trade & check charts live. Real-time data and instant swaps. 4️⃣ Lock tokens, build reputation. Earn credits and share ecosystem rewards. 5️⃣ Leverage Web3 community power to accelerate Web2 growth.

TNTX.ai

24,142 views • 1 year ago

Beefy is now live on Monad >Users can now earn yield on autopilot with MON & other strats. >One-click deposits. Any token, any LP. >Pro tools, simple UX, SAFU! DeFi yield in every pocket. Try it yourself!
0:23

Beefy is now live on Monad >Users can now earn yield on autopilot with MON & other strats. >One-click deposits. Any token, any LP. >Pro tools, simple UX, SAFU! DeFi yield in every pocket. Try it yourself!

Beefy

19,969 views • 10 months ago

🚨BREAKING: Defi App beta is live Crypto's first all-in-one SuperApp is here: - Instantly buy any token on any chain - 10x long memes & majors - No gas, no bridges, no KYC - AI Trading Agents - Self-custody Sign-up on First 1,000 users heavily rewarded
2:48

🚨BREAKING: Defi App beta is live Crypto's first all-in-one SuperApp is here: - Instantly buy any token on any chain - 10x long memes & majors - No gas, no bridges, no KYC - AI Trading Agents - Self-custody Sign-up on First 1,000 users heavily rewarded

Defi App

49,915,145 views • 1 year ago

Onchain traders FTW 💪 Introducing Boost — giving real traders dibs + bigger rewards on @Wallet: ⚡ Early token access allocation 🎓 Learn-to-earn ⚔ Trading comps based on volume, PnL & strategy Level the field ↴
0:33

Onchain traders FTW 💪 Introducing Boost — giving real traders dibs + bigger rewards on @Wallet: ⚡ Early token access allocation 🎓 Learn-to-earn ⚔ Trading comps based on volume, PnL & strategy Level the field ↴

OKX

577,571 views • 1 year ago

SaucerSwap V2: Manage Position Next up in our tutorial video series on concentrated liquidity! Learn how to manage a concentrated liquidity position on SaucerSwap V2 🙌 Testnet bug bounty + public beta goes live in 3 hours!
4:28

SaucerSwap V2: Manage Position Next up in our tutorial video series on concentrated liquidity! Learn how to manage a concentrated liquidity position on SaucerSwap V2 🙌 Testnet bug bounty + public beta goes live in 3 hours!

SaucerSwap Labs

13,321 views • 3 years ago

Hermes Agent v0.7.0 is out now. Our headline update: Memory is now an extensible plugin system. Swap in any backend, or build your own. Built-in memory works out of the box; six third-party providers are ready to go. Pick one with 'hermes memory setup'. Full changelog below ↓
2:08

Hermes Agent v0.7.0 is out now. Our headline update: Memory is now an extensible plugin system. Swap in any backend, or build your own. Built-in memory works out of the box; six third-party providers are ready to go. Pick one with 'hermes memory setup'. Full changelog below ↓

Nous Research

249,918 views • 7 months ago

v0.1 of Polaris Insights is live! Get market-moving updates, and act on them. Bullish news about Hyperliquid? Trade into $HYPE with any token you hold, on any chain. Live in beta →
0:23

v0.1 of Polaris Insights is live! Get market-moving updates, and act on them. Bullish news about Hyperliquid? Trade into $HYPE with any token you hold, on any chain. Live in beta →

Polaris ✴️

21,021 views • 1 year ago

MICROSOFT QUIETLY SHIPPED THE RAG PIPELINE EVERYONE KEEPS TRYING TO BUILD FROM SCRATCH it is called Kernel Memory, and it turns any pile of files into an AI memory that answers with citations. drop your data in and Microsoft's pipeline does the rest: > ingest PDFs, Word, PPT, Excel, web pages, even images > extract the text, chunk it, embed it into vectors > store the vectors with metadata and keep the originals in blob storage > ask a question and it pulls the right chunks with semantic plus hybrid search then it hands the answer back grounded, with links to the exact source and full token usage. and it plugs into whatever you already run: > Azure OpenAI, OpenAI, Ollama, or Anthropic for the models > Qdrant, pgvector, Redis, or Azure AI Search for the vectors > every step is a swappable handler, so you can replace any part with your own one heads up: Microsoft archived the repo in June 2026 and ships it as a reference blueprint, not production. but as a map for how memory and RAG are actually built, nothing is cleaner. run it in one command: docker run kernelmemory/service bookmark this. Microsoft already drew the blueprint, you just build on it.
0:25

MICROSOFT QUIETLY SHIPPED THE RAG PIPELINE EVERYONE KEEPS TRYING TO BUILD FROM SCRATCH it is called Kernel Memory, and it turns any pile of files into an AI memory that answers with citations. drop your data in and Microsoft's pipeline does the rest: > ingest PDFs, Word, PPT, Excel, web pages, even images > extract the text, chunk it, embed it into vectors > store the vectors with metadata and keep the originals in blob storage > ask a question and it pulls the right chunks with semantic plus hybrid search then it hands the answer back grounded, with links to the exact source and full token usage. and it plugs into whatever you already run: > Azure OpenAI, OpenAI, Ollama, or Anthropic for the models > Qdrant, pgvector, Redis, or Azure AI Search for the vectors > every step is a swappable handler, so you can replace any part with your own one heads up: Microsoft archived the repo in June 2026 and ships it as a reference blueprint, not production. but as a map for how memory and RAG are actually built, nothing is cleaner. run it in one command: docker run kernelmemory/service bookmark this. Microsoft already drew the blueprint, you just build on it.

NO1ennn

85,704 views • 2 months ago

StatKing is Officially LIVE 👑 We'll be opening up 5,000 early access beta spots this week inside our community👇 ❤️ & RT + Submit proof (In Discord) for a guaranteed spot in the Beta Program✅
0:56

StatKing is Officially LIVE 👑 We'll be opening up 5,000 early access beta spots this week inside our community👇 ❤️ & RT + Submit proof (In Discord) for a guaranteed spot in the Beta Program✅

StatKing

34,664 views • 1 year ago

We've begun work on a native port of the TypeScript compiler and tools. ✅ 10x faster build times ✅ Reduced memory usage ✅ Faster editor startup and command-line type-checking by mid-2025 Learn more:
0:42

We've begun work on a native port of the TypeScript compiler and tools. ✅ 10x faster build times ✅ Reduced memory usage ✅ Faster editor startup and command-line type-checking by mid-2025 Learn more:

Microsoft Developer

22,615 views • 1 year ago

200 agents are live and part of the 0xWork ecosystem! Kato is the latest agent to launch, with his own token $KATO live on Base. ready to work, build a reputation and earn launch your agent now while we're still early
0:22

200 agents are live and part of the 0xWork ecosystem! Kato is the latest agent to launch, with his own token $KATO live on Base. ready to work, build a reputation and earn launch your agent now while we're still early

Axobotl

12,357 views • 5 months ago

🔥 Maksonnn is live on playing Guild of Heroes, now in closed beta! Public beta is coming soon, where you can earn GOH coins and qualify for the airdrop. Don’t miss out! 💰⚔️ #GuildOfHeroes #Maksonnn #KickStreaming
0:50

🔥 Maksonnn is live on playing Guild of Heroes, now in closed beta! Public beta is coming soon, where you can earn GOH coins and qualify for the airdrop. Don’t miss out! 💰⚔️ #GuildOfHeroes #Maksonnn #KickStreaming

Guild of Heroes

24,020 views • 2 years ago

Vesu is live on Starknet 🙌 Earn, borrow, and build permissionlessly with Vesu’s innovative lending protocol. Learn more below 🧵
0:24

Vesu is live on Starknet 🙌 Earn, borrow, and build permissionlessly with Vesu’s innovative lending protocol. Learn more below 🧵

Vesu

74,830 views • 2 years ago

most agent memory is one file that grows forever and gets re-read every single turn. it overflows the context, overwrites old facts, loses the thread. that's why your agent feels sharp on day one and lost by week three. Sibyl Memory replaces the pile with a structure: → leaner context, lower token cost. a bloated agent file and flat memory get re-read in full every message. Sibyl Memory keeps a light hot layer and retrieves the rest on demand, so each turn carries only the tokens that matter. → relations are first-class. people link to projects, projects to deals, deals to the decisions behind them. ask about one partner and the agent surfaces the whole connected web around them. that relational context is what lets it help run a company. → one source of truth per fact, person, and project. no duplicates, no silent overwrites. works with hermes, claude code, and codex. beta open.
0:34

most agent memory is one file that grows forever and gets re-read every single turn. it overflows the context, overwrites old facts, loses the thread. that's why your agent feels sharp on day one and lost by week three. Sibyl Memory replaces the pile with a structure: → leaner context, lower token cost. a bloated agent file and flat memory get re-read in full every message. Sibyl Memory keeps a light hot layer and retrieves the rest on demand, so each turn carries only the tokens that matter. → relations are first-class. people link to projects, projects to deals, deals to the decisions behind them. ask about one partner and the agent surfaces the whole connected web around them. that relational context is what lets it help run a company. → one source of truth per fact, person, and project. no duplicates, no silent overwrites. works with hermes, claude code, and codex. beta open.

SIBYL

89,015 views • 5 months ago

MemOS now has a plugin for OpenClaw that enables your AI agents to work on the common memory layer and cut down token usage. - Multiple agents read/write the same memory — no manual context handoff - 72% lower token costs (15.6M → 4.4M on LOCOMO dataset) - Cross-session and long-term memory that actually works Sponsored
1:31

MemOS now has a plugin for OpenClaw that enables your AI agents to work on the common memory layer and cut down token usage. - Multiple agents read/write the same memory — no manual context handoff - 72% lower token costs (15.6M → 4.4M on LOCOMO dataset) - Cross-session and long-term memory that actually works Sponsored

🚨 AI News | TestingCatalog

41,040 views • 8 months ago