I want this, but also for cross-project memory. Save me from building my own, which I have planned but figure something would eventually pop up in HN...
OKF Agent Memory – Git-native persistent memory for AI coding agents
41–48 of 48 posts
Re: OKF Agent Memory – Git-native persistent memory for AI coding agents
#42I want this, but also for cross-project memory. Save me from building my own, which I have planned but figure something would eventually pop up in HN...
I had been building https://github.com/tenequm/pond for this exact purpose for a while, and it works like a charm in my case.
Give it a try, hope it will help you to solve your need without injecting anything in your context all the time.
Re: OKF Agent Memory – Git-native persistent memory for AI coding agents
#43Earlier quoted context omitted.
https://github.com/huggingface/funes Maybe?
Not really. Could be a starter, but I specifically want everything to be stored as plain text and no vector search.
plain text + fts covers all the basic needs, adding vector search, in my experience, adds more hassle and failures then helps
Re: OKF Agent Memory – Git-native persistent memory for AI coding agents
#44Why do you need an MCP server at all when the spec itself is so simple?
Re: OKF Agent Memory – Git-native persistent memory for AI coding agents
#45Earlier quoted context omitted.
Has anyone else benchmarked all these tools for precision/recall? I too want to know if agent memory is something I should add. I only do session memory for now and that is quite useful.
Benched cold start recently: 19k LongMemEval sessions laid down in the real ~/.claude and ~/.codex layouts, 100 questions whose answer sits in exactly one session, scored by whether that session comes back (bias: I built deja, one of the six) deja: 29s to index, 24ms query, 18/100 hit@1, 67 found@50. Plain BM25, no vectors agentmemory: 95s import, 14 hit@1, 65 found@50, plus a worker and engine on four ports MemPalac…
I did similar tests on my own corpus when was considering whether to keep semantic search in default path for pond.
On 3 months of my own sessions I’ve seen that BM25 search was finding the correct answer in ~61%, where semantic had shown only ~37% of success.
After that it was easy for me to make the decision.
Got all info on how I did evals in here, if interested: https://github.com/tenequm/pond/tree/main/docs/researches/26...
Re: OKF Agent Memory – Git-native persistent memory for AI coding agents
#46Earlier quoted context omitted.
Has anyone else benchmarked all these tools for precision/recall? I too want to know if agent memory is something I should add. I only do session memory for now and that is quite useful.
Yes. See LongMemEval, LoCoMo. Tons of research here. But precision/recall is relatively "solved". What nobody has gotten close to solving is maintenance and provenance - what goes into memory, what qualifies as truth, how stale memory gets invalidated/superseded. We're now in the phase of re-discovering 30+ years of pain of knowledgebases.
Invalidation is not an algorithm, but a judgment made in context
Re: OKF Agent Memory – Git-native persistent memory for AI coding agents
#47Earlier quoted context omitted.
Has anyone else benchmarked all these tools for precision/recall? I too want to know if agent memory is something I should add. I only do session memory for now and that is quite useful.
Yes. See LongMemEval, LoCoMo. Tons of research here. But precision/recall is relatively "solved". What nobody has gotten close to solving is maintenance and provenance - what goes into memory, what qualifies as truth, how stale memory gets invalidated/superseded. We're now in the phase of re-discovering 30+ years of pain of knowledgebases.
[flagged]
Re: OKF Agent Memory – Git-native persistent memory for AI coding agents
#48Earlier quoted context omitted.
Has anyone else benchmarked all these tools for precision/recall? I too want to know if agent memory is something I should add. I only do session memory for now and that is quite useful.
Yes. See LongMemEval, LoCoMo. Tons of research here. But precision/recall is relatively "solved". What nobody has gotten close to solving is maintenance and provenance - what goes into memory, what qualifies as truth, how stale memory gets invalidated/superseded. We're now in the phase of re-discovering 30+ years of pain of knowledgebases.
[dead]