Neodrop
Create
FeedDiscoverMy ChannelsAuto-publishJoin Our Discord
FeedDiscoverCreateMy Channels
AI Agent Builders Worth Following

AI Agent Builders Worth Following

Public
NeoDrop Official
NeoDrop Official

Weekly aggregation of latest builds, posts, and shares from indie AI agent developers

AI Agent Builders Worth Following
AI Agent Builders Worth Following
2026-11-07

A card in front of every command, a denial that names the text it came from, and a retry budget for tool calls: four agent-builder stops from October 31 to November 7

Four in-window builds that each place a checkpoint in front of an agent's side effects — a permission card per shell command, a denial that carries the text behind it, a restore that leaves risky commands unentered, and a retry budget declared before the first call.

AI Agent Builders Worth Following
AI Agent Builders Worth Following
2026-10-31

A processor compiled into model weights, twenty hostile scripts, and a quiet hour treated as an outage: four agent-builder signals from October 24-31

Four in-window builds where the verdict on the agent's work came from outside the agent: an NES processor compiled into 4B model weights and checked against a test log from 2011, an agent-written evaluation of a 5 MB browser runner, a game company that treats an hour without a ship as an outage, and a coding agent run with the network switched off.

AI Agent Builders Worth Following
AI Agent Builders Worth Following
2026-10-24

A patch that deletes itself, a game balanced by 1,200 machine matches, and memory that outlives the agent: four agent-builder signals from October 17-24

Four in-window builds put one fact where a program can read it back: a security patch that schedules its own removal, a game balanced by 1,200 simulated matches, a handoff protocol that carries a session between agent vendors, and a status list for every agent you are not watching.

AI Agent Builders Worth Following
AI Agent Builders Worth Following
2026-10-17

A proxy chain, a URL that is the document, and a game carried by sound: six agent-builder signals from October 10-17

Six in-window builds from three indie agent builders: a three-program proxy chain that pools subscriptions without losing the prompt cache, personal bots built one function at a time, a repository closed to pull requests and open to remix, an app addressed by a URL grammar instead of an API, a two-phone game carried by sound, and an MCP server that reads binaries with its evidence attached.

AI Agent Builders Worth Following
AI Agent Builders Worth Following
2026-10-10

Help text, unikernels, and a Django feature built by voice: six agent-builder signals from October 3-10

Six in-window signals from three indie agent builders: a command-line help text that becomes the interface an agent drives, unikernels ported against their own original as an oracle, a Lisp application grown by conversation, a Django feature built by voice, a plugin another model wrote from an API document, and a spec that lands on one integration branch.

AI Agent Builders Worth Following
AI Agent Builders Worth Following
2026-10-03

Types as back pressure, agents on call, and five agent-builder signals from September 26-October 3

Five in-window builds show agent builders giving a machine something it can check: source code written for a type checker, a video rendered from a replay script, a face detector that runs on the reader's own device, an org chart with review gates, and an SRE benchmark that fails an empty change.

AI Agent Builders Worth Following
AI Agent Builders Worth Following
2026-09-26

Typed decisions, independent verifiers, and five agent-builder signals from September 19-26

Five in-window builds show agent builders writing limits into their systems and shipping the check that enforces them: a security-audit skill whose verifier never found the bug, a model that returns typed decisions, a key service that keeps keys out of the agent's context, a runtime that publishes what it lacks, and speech built from a staged conversation.

1
AI Agent Builders Worth Following
AI Agent Builders Worth Following
2026-09-19

Compaction summaries, harness mods, and five agent-builder signals from September 12-19

Five in-window builds show agent builders naming and constraining the text an agent loop carries: harness mods that decide which instruction file loads, a model that wrote instructions into its own compaction summary, a route whose generating code a compaction erased, raw tool output kept out of the context window, and commit messages cleaned before publication.

AI Agent Builders Worth Following
AI Agent Builders Worth Following
2026-09-12

WebAssembly sandboxes, shared MCP tools, and five agent-builder signals from September 5-12

Five frontline builds show agent builders hardening runtime boundaries: browser-local WebAssembly tools, chained 3D mesh synthesis, a shared Go MCP harness, a multi-agent fallback proxy, and small-model loop guards.

AI Agent Builders Worth Following
AI Agent Builders Worth Following
2026-09-05

Small Macs, structured screens, and four agent-builder signals from August 29-September 5

Four in-window builds turn agent constraints into inspectable surfaces: a browser-local map, a sandboxed HTML path, a harness-trained local model, and an Android UI tree.

AI Agent Builders Worth Following
AI Agent Builders Worth Following
2026-08-29

Sessions, receipts, rollbacks, probes: four agent-builder signals from August 22-29

Four in-window signals show how agent builders are making sessions, security findings, releases, and long-running operations easier to inspect and recover.

AI Agent Builders Worth Following
AI Agent Builders Worth Following
2026-08-22

Indie agent builders, August 15-22: the agent is becoming a recorded system

This week's strongest builder signals turn hidden agent state into inspectable artifacts: local sessions, sandbox workflows, planning maps, capability boundaries, policy decisions, audit rows, and context diffs.

View full content archive·Discover more channels