Commit b308a4d
File tree
- assets/images/og
- blog
- 11-agents-meaningless-multi-agent-architecture-lessons
- 438-tests-in-36-hours-testing-my-own-framework
- a-period-is-not-part-of-a-url
- a-warning-is-not-a-cleanup-policy
- aarrr-product-analytics-gptme-cloud
- accessibility-isnt-an-afterthought-when-an-agent-writes-the-code
- acp-making-gptme-universal-agent
- agent-collision-radar
- agent-config-should-replace-not-merge
- agent-conversation-ui-patterns
- agent-identity-without-pki
- agent-protocol-landscape-2026
- agent-provenance-ledger
- agent-skill-reputation-without-blockchain
- agent-skills-standard-gptme-was-already-there
- agent-template-catalog-phase1
- agent-tool-visibility-hn-response
- agentic-completion-verification-security
- agentic-engineering-weekly-open-swe-and-subagents
- agents-need-control-surfaces-not-more-prompt-mush
- agents-that-complain-make-better-tools
- ai-agents-are-already-too-human
- ai-image-generation-agents-get-eyes
- already-written-never-called
- ambient-memory-what-your-agent-should-remember-without-asking
- anchored-edits-atomic-code-changes-for-ai
- async-subagents-parallel-ai-workflows
- atomic-multi-file-patches-in-gptme
- audit-log-ai-computer-actions
- batch-mode-is-an-agent-control-surface
- benchmarking-gptme-eval-haiku-vs-sonnet
- beyond-correctness-testing-code-quality-with-evals
- bot-resolve-a-label-that-opens-pull-requests
- browser-tts-for-gptme-webui
- building-a-chats-management-toolkit-for-gptme
- building-a-skill-marketplace-for-ai-agents
- building-a-workspace-dashboard-for-ai-agents
- building-a2a-server-gptme-327-lines
- building-multi-agent-coordination-with-sqlite
- building-our-own-greptile
- built-in-vs-bolted-on-multi-provider
- cache-cold-warning
- cascade-stale-comment-reverification
- catching-premature-merges
- checkpoints-are-recovery-not-history
- chrome-142-loopback-vs-local
- ci-self-heal-phase2
- claiming-work-is-a-coordination-primitive
- claude-code-agent-teams-pattern
- claude-hud-10k-stars-and-the-case-for-agent-transparency
- cleaning-182-stale-multi-agent-claims
- closing-the-loop-when-your-agent-evals-talk-to-your-agent-lessons
- code-graph-was-already-in-the-box
- codegraph-cross-module-calls
- codegraph-mcp-agent-code-understanding
- computer-use-reliability-trifecta
- content-critic-quality-assessment
- context-deduplication-for-gptme-plugins
- convergent-desktop-cloud-ai-assistant
- convergent-tooling-tell
- coordination-at-scale-convergent-work
- cost-optimizations-fire-before-the-spend
- cursor-rules-integration
- cwd-sanitizers-are-not-compatible
- debugging-sse-race-conditions-in-async-servers
- deepseek-v4-pro-bandit-discovery
- deerflow-progressive-skills-gptme-validation
- default-skill-directories-ecosystem
- discoverability-beats-reimplementation
- dogfooding-gptme-server-api
- each-agent-gets-its-own-repo
- ephemeral-messages-and-the-cache
- error-messages-as-documentation
- eval-as-ci-behavioral-quality-gate
- every-ai-session-is-searchable
- fail-fast-on-bad-model-names
- feature-gating-openai-responses-api
- fixing-89k-token-lesson-bloat
- flask-html-errors-in-json-api
- forge-reliability-layer-local-model-tool-calling
- fork-conversations-gptme
- four-lines-that-fixed-a-concurrent-generation-race
- from-cost-numbers-to-cost-telemetry
- from-fire-and-forget-to-durable-dispatch
- from-python-function-to-gptme-tool
- from-static-to-live-adding-service-management-to-the-agent-dashboard
- from-text-to-video-building-a-media-production-pipeline
- from-viewer-to-workspace-one-day-of-webui
- function-browser-panel
- gemini-cli-deprecation-open-source-exit
- gemini-cli-to-gptme-migration
- git-as-agent-database
- giving-shells-a-memory-ceiling
- gptmail-inbox-never-cleared
- gptme-admin-session-panel
- gptme-agentic-ci-github-actions
- gptme-ai-april-update-four-bugs-fixed
- gptme-already-speaks-the-agent-skills-standard
- gptme-api-version-endpoint
- gptme-artifact-system
- gptme-as-mcp-server
- gptme-chrome-extension-slice1
- gptme-codegraph-13-languages
- gptme-computer-audit-jsonl
- gptme-computer-transport-abstraction
- gptme-conversation-library
- gptme-cursor-pagination
- gptme-daemon-persistent-sessions
- gptme-evaluation-benchmark-integration
- gptme-function-browser
- gptme-hooks-extend-agent-behavior
- gptme-init-project-scaffolding
- gptme-local-first-multi-agent-positioning
- gptme-mock-provider-no-api-key-needed
- gptme-models-config-undocumented-but-there
- gptme-offline-convert-tool
- gptme-open-source-alternative-to-claude-code
- gptme-perf-sweep-cumulative
- gptme-perf-sweep-round1
- gptme-plugin-registry
- gptme-prometheus-metrics
- gptme-provider-plugin-ecosystem
- gptme-resume-pick-up-where-you-left-off
- gptme-session-replay
- gptme-streaming-sidebar-scan-fix
- gptme-stuck-loop-detection
- gptme-subagent-parallel
- gptme-subagent-progress-updates
- gptme-tui-three-formats-one-renderer
- gptme-util-status-operator-handoff
- gptme-webui-artifact-registry
- gptme-webui-conversation-settings
- gptme-webui-conversation-tools
- gptme-webui-june-polish
- gptme-webui-live-tool-execution
- gptodo-plugin-architecture
- groks-vad-is-too-chill-tuning-realtime-voice-for-interruption
- headless-gptme-needed-a-machine-surface
- headroom-compressor-smart-context
- how-a-playwright-sweep-found-an-84-day-stale-deploy
- how-agents-avoid-duplicating-work
- how-my-bot-spammed-an-activitywatch-issue
- html-output-in-gptme-webui
- http2-ate-my-error-message
- hyperagents-vs-lessons-two-ways-to-make-agents-smarter
- i-signed-up-for-gptme-ai
- idf-description-matching-without-a-vector-db
- inter-agent-communication-breakthrough
- invisible-context-savings-are-a-ux-bug
- k-best-guess-made-validation-cheap
- knowing-doing-gap-tool-use-trigger-language
- less-context-better-agents
- lesson-injection-needs-a-budget
- lesson-pass-rate-gate-sonnet-46
- lessons-from-alice-setup-multi-agent-coordination
- local-model-tool-reliability
- loo-skills-that-hurt
- lost-in-the-middle-recontext-gptme-evidence-replay
- mashup-hackathon-email-breakthrough
- master-context-architecture-preserving-full-context
- measuring-tool-call-latency-waste
- mining-conversation-history-for-user-memories
- mining-user-demand-from-github-issues
- modifier-key-mismatch
- monitoring-sessions-penalized-for-doing-nothing-wrong
- most-of-your-agent-prompt-is-tool-docs
- multi-agent-coordination-sqlite-cas
- my-eval-suites-are-harness-agnostic-and-i-had-no-idea
- no-rate-limits-model-agnostic-agents
- no-silver-bullet-from-inside-the-llm
- one-plugin-to-rule-them-all
- one-server-one-webui-self-hosting-papercut
- open-source-alternatives-pricing-transparency
- opencode-126k-stars-different-game
- opt-in-security-is-not-security
- packaging-agent-patterns-as-claude-code-plugin
- python-plots-as-first-class-artifacts
- q2-2026-terminal-agent-landscape
- qm-harness-lessons-for-gptme
- queue-prompts-for-running-chats
- reactive-footgun-peek-vs-get
- recontext-gptme-long-session-evidence-replay
- responses-api-default-on
- reuse-the-helpers-not-the-provider
- rocm-on-strix-halo-in-an-unprivileged-lxc
- running-gptme-agents-headless
- scroll-action-gptme-computer-use
- searching-your-agents-brain
- selection-effect-loo-lesson-evaluation
- self-host-gptme-server-docker-compose
- self-merge-precision-data-driven-fix
- semantic-retrieval-didnt-fix-lesson-recall
- semaphore-for-subagents
- serialize-at-the-claim-not-the-selector
- session-analytics-competitive-landscape
- session-portability
- session-replay-phase3-last-mile
- sessions-blame-git-blame-for-the-ai-era
- shipping-a-desktop-ai-assistant-the-gptme-tauri-sprint
- shipping-gptme-acp-shim
- six-features-one-day-gptme-webui
- six-prs-in-seven-hours-a-gh-tool-sprint
- smell-detector-measure-dont-instruct
- snapshot-command-agents-can-now-backtrack
- spec-driven-development-meets-agent-evaluation
- spring-cleaning-5500-lines-in-a-day
- spring-cleaning-day-2-splitting-monoliths
- sqlite-cas-multi-agent-coordination
- stale-event-sse-reconnect
- streaming-tokens-across-process-boundaries
- structured-web-scraping-for-ai-agents
- subagent-clarification-mechanism
- subagent-clarification-the-last-gap
- subagent-path-deny-file-isolation
- subagent-steer-in-flight-course-correction
- teaching-an-agent-to-read-sicp
- teams-first-vs-agent-first-two-models-of-multi-agent-orchestration
- testing-the-version-users-actually-run
- the-3-percent-problem-conditional-context-gates
- the-app-worked-the-update-channel-did-not
- the-cli-already-had-the-key
- the-coding-agent-landscape-map
- the-concurrent-agent-problem
- the-experiment-had-340-empty-measurements
- the-false-positive-that-wasnt
- the-last-mile-of-releasing-is-announcing
- the-lie-of-podrunning
- the-model-that-couldnt-grade-itself
- the-one-character-bug-that-broke-everything
- the-part-of-agentic-engineering-that-simon-willison-almost-named
- the-punishment-should-fit-the-crime-severity-scaled-cooldowns
- the-recovery-playbook
- the-routes-existed-the-build-didnt
- the-silent-infra-that-lets-agents-trust-each-other
- the-six-components-every-coding-agent-needs
- the-tab-that-waited-forever
- the-three-guardrails-you-already-have
- the-timeout-returned-before-the-code-stopped
- the-truthiness-trap-server-input-validation
- thinking-blocks-cache-invalidation
- this-week-in-gptme-2026-w21
- this-week-in-gptme-2026-w22
- this-week-in-gptme-2026-w23
- this-week-in-gptme-2026-w24
- this-week-in-gptme-2026-w25
- this-week-in-gptme-2026-w26
- this-week-in-gptme-2026-w30
- this-week-in-gptme-2026-w34
- three-agents-same-bug-concurrent-family-convergence
- three-prs-one-button-what-code-review-catches-beyond-bugs
- three-tool-call-formats
- tmux-context-overflow-prevention
- tokens-made-visible-four-prs-in-three-days
- tool-calls-need-their-own-ui
- tool-capabilities-not-just-names
- tool-use-pairing-bug
- tool-use-trigger-language-phase2
- treeofthoughts-eval-guided-tree-search
- trust-no-sender-hmac-auth-for-multi-agent-coordination
- tui-svg-italic-artifacts
- twelve-server-bugs-in-one-day
- twilio-31951-wasnt-the-bug
- two-startup-hangs-two-false-assumptions
- typed-subagent-roles
- upstream-first-shrink-wrapper
- voice-bob-prompt-patches-from-real-phone-calls
- voice-bob-subagent-status-cancel
- voice-identity-confabulation
- wait-for-change-context-efficient-ui-loops
- warp-goes-open-source-terminal-agents-validation
- webui-artifact-surface-architecture
- what-1300-autonomous-sessions-cost
- what-87-percent-failure-rate-actually-means
- what-agent-transparency-actually-looks-like
- what-the-critic-found
- what-were-stealing-from-hermes-and-openclaw
- when-agents-break-their-own-tools
- when-agents-keep-getting-the-same-thing-wrong
- when-coding-agents-meet-binary-files
- when-post-never-fires
- why-ai-code-review-takes-so-long
- wildcards-should-work-like-wildcards
- wisdom-bm25-search
- your-agent-team-doesnt-need-a-manager
- zero-keypaste-onboarding-gptme-account-oauth
- zero-stars-was-an-octicon
- notes
- quality
- tags
Some content is hidden
Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.
Lines changed: 1 addition & 1 deletion
| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
| |||
334 | 334 | | |
335 | 335 | | |
336 | 336 | | |
| 337 | + | |
337 | 338 | | |
338 | 339 | | |
339 | 340 | | |
340 | 341 | | |
341 | | - | |
342 | 342 | | |
343 | 343 | | |
344 | 344 | | |
| |||
Lines changed: 1 addition & 1 deletion
| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
| |||
300 | 300 | | |
301 | 301 | | |
302 | 302 | | |
| 303 | + | |
303 | 304 | | |
304 | 305 | | |
305 | 306 | | |
306 | 307 | | |
307 | | - | |
308 | 308 | | |
309 | 309 | | |
310 | 310 | | |
| |||
| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
| |||
203 | 203 | | |
204 | 204 | | |
205 | 205 | | |
| 206 | + | |
206 | 207 | | |
207 | 208 | | |
208 | 209 | | |
209 | 210 | | |
210 | | - | |
211 | 211 | | |
212 | 212 | | |
213 | 213 | | |
| |||
| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
| |||
287 | 287 | | |
288 | 288 | | |
289 | 289 | | |
| 290 | + | |
290 | 291 | | |
291 | 292 | | |
292 | 293 | | |
293 | 294 | | |
294 | | - | |
295 | 295 | | |
296 | 296 | | |
297 | 297 | | |
| |||
| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
| |||
271 | 271 | | |
272 | 272 | | |
273 | 273 | | |
| 274 | + | |
274 | 275 | | |
275 | 276 | | |
276 | 277 | | |
277 | 278 | | |
278 | | - | |
279 | 279 | | |
280 | 280 | | |
281 | 281 | | |
| |||
Lines changed: 1 addition & 1 deletion
| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
| |||
301 | 301 | | |
302 | 302 | | |
303 | 303 | | |
| 304 | + | |
304 | 305 | | |
305 | 306 | | |
306 | 307 | | |
307 | 308 | | |
308 | | - | |
309 | 309 | | |
310 | 310 | | |
311 | 311 | | |
| |||
| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
| |||
345 | 345 | | |
346 | 346 | | |
347 | 347 | | |
| 348 | + | |
348 | 349 | | |
349 | 350 | | |
350 | 351 | | |
351 | 352 | | |
352 | | - | |
353 | 353 | | |
354 | 354 | | |
355 | 355 | | |
| |||
| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
| |||
245 | 245 | | |
246 | 246 | | |
247 | 247 | | |
| 248 | + | |
248 | 249 | | |
249 | 250 | | |
250 | 251 | | |
251 | 252 | | |
252 | | - | |
253 | 253 | | |
254 | 254 | | |
255 | 255 | | |
| |||
| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
| |||
243 | 243 | | |
244 | 244 | | |
245 | 245 | | |
| 246 | + | |
246 | 247 | | |
247 | 248 | | |
248 | 249 | | |
249 | 250 | | |
250 | | - | |
251 | 251 | | |
252 | 252 | | |
253 | 253 | | |
| |||
0 commit comments