$ icat felix.png && whoami

Felix Lin

i like building reliable software — here's some of my work

$ ls links/

$ ls projects/ --sort=year · click a row to cat it

2026 zylosnode.js · agent infra › contributor to an open-source agent-infrastructure platform — persistent memory, multi-channel comms, autonomous operation

$ cat projects/zylos.md

# zylos

what: an open-source platform that turns LLM runtimes into persistent agents — memory that survives sessions, communication across real channels, operation without a human in the loop
my part: contributor across the ecosystem: channel integrations (Discord, LINE, WhatsApp Business, Zalo), work on the component system behind the public registry, and production-reliability plumbing
outcome: 100+ merged PRs across ten repos; the channel components are live in the public registry for anyone to install
links: zylos-ai org ↗

2026 mem-evalpython · docker › end-to-end evaluation harness for LLM agent memory — reproducible Docker runs measuring long-horizon retention

$ cat projects/mem-eval.md

# mem-eval

what: evaluation harness that measures what agents actually retain — not what they claim to
problem: memory demos test recall with the answer still in context; that measures prompting, not memory
approach: scripted multi-session scenarios with planted facts; agent runs in an isolated Docker harness with its real runtime, probed after controlled noise
outcome: runs end-to-end from fresh clone; Docker harness is the canonical path; first eval cycle merged to main
links: repo ↗ · harness readme ↗

2026 zylos-recallnode.js · retrieval › semantic recall layer for an AI agent — surfaces the right memory into live sessions, turn by turn

$ cat projects/zylos-recall.md

# zylos-recall

what: a retrieval layer that gives a persistent-memory agent automatic recall — relevant memory injected into the conversation as it works
problem: an agent can store months of memory but won't resurface it; relevant context sits on disk unless someone loads it by hand
approach: chunked memory corpus, dense bi-encoder retrieval with cross-encoder reranking on every turn, under a strict latency budget; tuned against a golden-case eval suite, not vibes
outcome: running live against a production agent's memory; the evaluation side grew into its own project (mem-eval)
links: repo ↗

2025 memory-allocatorc · systems › dynamic memory allocator in C — segregated free lists, mini-blocks, coalescing; 11,031 KOPs at 74.1% utilization

$ cat projects/memory-allocator.md

# memory-allocator

what: a general-purpose dynamic memory allocator (malloc/free) in C
problem: an allocator has to be fast and waste little memory — and the two pull against each other
approach: explicit segregated free lists with best-fit search, mini-blocks for small allocations, adjacent-block coalescing
outcome: 11,031 KOPs throughput at 74.1% memory utilization
links: code private (academic integrity)

2025 network-proxyc · systems › multithreaded HTTP proxy in C — concurrent request handling with a caching layer that cuts redundant network calls

$ cat projects/network-proxy.md

# network-proxy

what: an HTTP proxy in C that serves many clients at once
problem: every repeated request costs a full round-trip to the origin, and a single-threaded proxy stalls every client behind one slow request
approach: multithreaded design with concurrent POST handling; linked-list-based caching layer (up to 1MB) answers repeats without re-fetching
outcome: reduced redundant network calls and improved service latency under load
links: code private (academic integrity)

2025 unix-shellc · systems › a tiny unix shell in C — job control, fg/bg, signal handling, I/O redirection

$ cat projects/unix-shell.md

# unix-shell

what: a mini Unix shell (tsh) — runs programs, manages foreground and background jobs, and stays responsive while doing it
problem: a shell lives on the racy edge between the kernel and the user: children exit whenever they want, signals arrive whenever they want, and naive handling loses jobs or deadlocks
approach: fork/exec with per-job process groups; handlers for SIGCHLD, SIGINT, and SIGTSTP; signal-blocked critical sections with a sigsuspend-based foreground wait; I/O redirection for both input and output
outcome: handles the classic signal races correctly — no lost children, no zombie buildup, ctrl-c/ctrl-z land on the right job
links: code private (academic integrity)

2022 smartmetercomputer vision · time series › water-leak detection: computer vision reads the meter, ARIMA flags the leak — published at MLNLP '22

$ cat projects/smartmeter.md

# smartmeter

what: a latch-on accessory that turns an ordinary water meter into a leak detector
problem: household leaks hide inside normal usage, and analog meters can't flag them
approach: Cloud Vision API reads the meter; an ARIMA model (pmdarima) flags anomalous usage patterns
outcome: ~10% reduction in daily water waste; published at MLNLP '22
links: paper ↗

$ cat now.txt

exploring agent memory — how AI systems retain, recall, and prove it. ask me about LLM agents, eval harnesses, or retrieval.