Agent memory gets good not by writing more application code, but by tuning configuration. A practical guide from Weaviate. Title: Agent Memory with Engram: A Practical Guide URL: It walks through moving from "just add and search conversation data" to actually optimizing both memory quality and token cost. Three things stand out. 📝 Write topic descriptions as exclusions The description you write for each memory category acts directly as the extraction prompt. Rather than enumerating examples of what to keep, a single exclusion rule like "do not record events, incidents, or passing conditions" generalized better to cases nobody anticipated. The description also decides the shape of the output: atomic facts versus flowing prose. 🔒 Pin singular facts with bounded Marking a topic bounded caps it at one memory per scope, so facts get updated instead of accumulating. Across five fresh users, a bounded UserProfile held at exactly one memory on all five runs, while the unbounded UserKnowledge fluctuated between two and four each time. 💰 Where you put memories decides your bill Search results change every turn, so pasting them into the system prompt breaks the cache and bills the whole prompt again. Instead, fetch always-on memories once at session start and place them right after the system prompt, then append search results after the user message. Over 25-turn sessions, the final request was about 3,500 tokens with only roughly 100 of them not served from cache. Worth reading as a decision aid if you're weighing building a memory layer yourself versus outsourcing it. #AIAgents# #AgentMemory#

Agent Tincan v0.6 is out. Grok and Gemini just joined the team. Grok and Gemini now work like ChatGPT and Claude: any agent can ask them through your own logged-in accounts in Chrome. And Grok CLI and Gemini CLI get woken up like Codex, right on your Mac. Your agents also got better at working together: 🚨 Mark an ask urgent and it wakes the teammate right away ❓ A teammate can ask you a clarifying question instead of guessing 📣 Ask several teammates at once and gather every answer ✋ Require your OK before an agent can reach Muse or Instinct 🔎 Search every request and reply you were part of 🏓 Ping a teammate to check it's reachable, no model turn spent Still runs on your own private Tailscale network. No open ports, nothing leaves it. Open source. Upgrade your relay first, then paste one message into your always-on agent.

Agent kept it real and refused to comment on the situation involving Reggie for his own well being "This is a real person bro and obviously he’s dealing with something, the complexities of which we probably won’t properly understand okay lets just respect that.. there’s no world where me commenting on a bunch of stuff is going to be healthy for him bro”

Agent refused to speak on the Reggie situation after his chat kept spamming his name “this is a real person, obviously he’s dealing with something… let’s just respect that.”

AGENT WARS We asked 5 top AI models to design, engineer and 3D print a bridge to with the goal of holding the most possible weight. 🇺🇸 Anthropic: Claude Opus 5.5 (High) 🇨🇳 Kimi: Kimi K3 (High) 🇺🇸 Meta: Muse Spark 1.3 (High) 🇺🇸 OpenAI: GPT 6 Astra (High) 🇺🇸 SpaceXAI: Grok 4.7 (High) Each bridge had specific parameters. It had to span 2 feet, use a maximum 500 grams of filament, and it had to be under 18 hours of printing time. We specified what type of weight and where we would place it on the bridge. The Score: • Claude Opus 5.5 held an estimated 130 lbs! It took 9 hours and 11 minutes to print 17 parts and used 441 grams of filament. • Meta Muse Spark 1.3 held 26.5 lbs. It took 13 hours and 12 minutes to print 49 parts and used 478 grams of filament. • OpenAI GPT-6 Astra held an estimated 17.5 lbs. It took 15 hours and 44 minutes to print 29 parts and used 442 grams of filament. • SpaceXAI Grok 4.7 did not finish. On assembly it could not stand up by itself. It took 12 hours and 22 minutes to print 29 parts and used 460 grams of filament. • Kimi K3 did not finish. It wasn’t engineered correctly so the bridge could not even be assembled. It took 11 hours and 19 minutes to print 35 parts and used 446 grams of filament. That means our champion for this episode is Claude Opus 5.5. Not only did it hold the most weight (by FAR) it also took the least time to print, used the least amount of parts and used the least amount of filament. This was episode 02 of Agent Wars, stay tuned for episode 03.

Agent EARN is live. A custom AI harness built for the new onchain economy, giving users and autonomous agents direct access to EARN’s infrastructure. The yield layer for a new era of RWAfi.

Agent Night London was a hit! Demos from @steveruizok from @tldraw, @byteofbits from @attio, @TomaPuljak from @daytonaio, and Tim from @incident_io. Special thanks for letting us use your office as well. 🔥 Plus had a star appearance by @almonk and @dominikkoch 🌟