Ash Lewis
@ash_csx
founder @ 4X founder. Forbes 30u30
655 Following 5.7K Followers
Most graph-based memory stacks rely on an LLM to do the extraction work, but that gets expensive fast.
The extraction layer feeding an agent's memory should be cheap enough to run constantly as new data becomes available.
We're teaming up with @cognee_ on September 3rd in Berlin to host an event on how smaller, local models can fit into that agent memory pipeline.
@m_newhaus, from our technical team, will demo how GLiNER handles entity and relation extraction for knowledge graphs, and @tricalt will be talking about why running small models locally beats frontier LLMs on memory tasks.
🔗 to sign up:
Show more
10,000 devs signed up for Pioneer last week, here are some of the updates we shipped:
• 15+ models (Opus 4.8 day-zero, GPT-5.5)
• Agent integrations: Codex, Claude Code, Hermes, OpenClaw
• Revamped CLI
• Upgraded our auth and reasoning controls
At @fastinoAI, we've started running our own Claude Code and Codex agents on Pioneer, and we’re already seeing improvements in both accuracy and cost.
Agent integration guide:
Show more
