convez.ai
MCP Server
DaeSeokSong

afterglow-claude-mcp

DaeSeokSong/afterglow-claude-mcp

Ver no GitHub
InicialPluginScore · de 0 a 100

Persona-based knowledge preservation MCP for Claude Code — turn departing teammates' expertise into queryable agents

Instalação

$npx convez-ai DaeSeokSong/afterglow-claude-mcp

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
1
Forks
0
Acompanhando
0
Saúde
42%
Último commit
há 3 meses
Versão
—
Issues abertas
1
Contribuidores
2

README

A tradução para o português deste README ainda está na fila.

Afterglow

Turn your departed teammate into an agent. Make offboarding seamless.


⏱ TL;DR

claude mcp add afterglow npx -y @daeseoksong/afterglow-mcp
# ...then, in Claude Code — 3 steps, no setup ceremony:
claude /afterglow create jiyoon --name "Jiyoon Lee" --role "Product Designer" --signer "Jiyoon Lee"
claude /afterglow learn  jiyoon --text "Trimming the step-2 explanation in half cut onboarding drop-off 22% → 9%."
claude /afterglow ask    jiyoon "Onboarding step-3 drop-off — how did you cut it?"
✦ Step-3 drop-off wasn't really a step-3 problem. We trimmed the step-2
  explanation in half and drop-off went 22% → 9%.        — Jiyoon · 91% confidence

  ↗ Confluence · DESIGN/onboarding-v2-postmortem
  ↗ ./materials/interview-2025-11-10.pdf · p. 14

New here? Just run /afterglow guide — it tells you exactly what to do for your current state. create --signer auto-initializes and activates in one call; learn adds the knowledge ask searches (no hunting for a hidden folder). No fine-tuning. Persona + RAG only — 100% compatible with Claude Code. Zero extra GPUs, embedding APIs, or external servers.


🗂 What's in this repo


✦ One-line install (MCP server)

claude mcp add afterglow npx -y @daeseoksong/afterglow-mcp

Then your first session — 3 steps, no init:

claude /afterglow guide                                              # (optional) what do I do? — state-aware orientation
claude /afterglow create jiyoon --name "Jiyoon Lee" --role "Product Designer" --signer "Jiyoon Lee"   # auto-inits + activates
claude /afterglow learn  jiyoon --text "<paste a note>"  # or --path ./notes/  or --url https://…
claude /afterglow ask    jiyoon "..."

--signer collapses create + sign into one call (drop it to keep the agent in draft until a separate sign). learn is how you give the agent something to retrieve — paste text, point at a file/folder under your working dir, or a URL.

See server/README.md for the full tool reference.

Two ways to invoke. Afterglow is an MCP server, so the actual tool calls are JSON like afterglow_handoff({slug: "jiyoon", action: "start"}). You can drive it either way:

  1. Natural language — say "initialize afterglow" and Claude picks the right tool.
  2. Slash command — from Claude Code's prompt box, /mcp__afterglow__<name> (e.g. /mcp__afterglow__init, /mcp__afterglow__ask) with argument auto-complete. (Exposed as MCP prompts — note the form is /mcp__afterglow__init, not /afterglow init.)

The claude /afterglow … notation in this README is shorthand for readability; in practice use one of the two ways above.

⌨ Slash commands — type afterglow: to use them (26)

How to invoke:

  1. Type afterglow: in the prompt box → a command list appears.
  2. Arrow-select the one you want → Tab.
  3. It becomes /mcp__afterglow__<name> with grey hints for the arguments — fill them in and run.

afterglow:init ⇥ /mcp__afterglow__init is a 1:1 mapping (afterglow: = what you type to find it, /mcp__afterglow__ = the resolved form). Natural language ("initialize afterglow") works identically. Tools with many arguments (interview attach/answer, …) are often easier in natural language.

🧭 You don't have to fill args in — missing required ones are guided. Run a tool with a required arg omitted and it returns numbered choices + help instead of erroring: e.g. just afterglow:ask → "①jiyoon ②jaehoon … ③type your own", and each argument is tagged [필수](required) / [선택](optional). (The (parens) in the tables below also mark optional args.)

Start here

CommandArgs (parens = optional)WhatExample
afterglow:guide(slug)"what do I do?" — state-aware orientationguide
afterglow:createslug name role (signer tenure bio)create an agent — auto-inits; signer activates in one callcreate → slug:jiyoon, name:Jiyoon Lee, role:Product Designer, signer:Jiyoon Lee
afterglow:learnslug (path / text / url title)add knowledge ask will search (file/folder, paste, or URL)learn → slug:jiyoon, text:"<paste a note>"
afterglow:askslug questionask the personaask → slug:jiyoon, question:how did you cut onboarding drop-off?

Setup · sign · archive

CommandArgs (parens = optional)WhatExample
afterglow:init(none)bootstrap ~/.claude/afterglow/ (usually unneeded — create auto-inits)afterglow:init
afterglow:signslug signersign consent → activesign → slug:jiyoon, signer:Jiyoon Lee
afterglow:resumeslugpaused/draft → activeresume → slug:jiyoon
afterglow:archiveaction(archive|restore|list) (slug)archive / restore / listarchive → action:archive, slug:jiyoon

Daily

CommandArgsWhatExample
afterglow:list(status)list agentslist / list → status:active
afterglow:status(none)global dashboardstatus
afterglow:inspectslugone agent in detailinspect → slug:jiyoon
afterglow:editslug (bio name role / open / revalidate)edit (fields / open in editor / revalidate)edit → slug:jiyoon, open:true
afterglow:historyslug (filter limit)event/conversation loghistory → slug:jiyoon, filter:payment

Ops · trust · access · audit

CommandArgsWhatExample
afterglow:correctslug action(feedback|edit-answer|save-rule|list) (feedback recordId)manual correctioncorrect → slug:jiyoon, action:feedback, feedback:settlement is weekly
afterglow:recalibrateslug (byTopic apply)auto-recalibrate confidencerecalibrate → slug:jiyoon, apply:true
afterglow:accessslug action(list|allow|deny|remove|set-default|check) (rule caller)call-permission policyaccess → slug:jiyoon, action:allow, rule:user:ykhyun
afterglow:audit(slug fast checkpoint)audit log + integrity verifyaudit → checkpoint:true
afterglow:versionslug action(list|diff|rollback|tag|snapshot) (versionA tag)persona version historyversion → slug:jiyoon, action:rollback, versionA:v3
afterglow:gcaction(list|prune-versions|purge-media|purge-archive) (slug apply)retention/cleanup (dry-run default)gc → action:prune-versions, slug:jiyoon

Interview · council

CommandArgsWhatExample
afterglow:handoffslug action(start|review|status|finalize|abort) (signer)self-review handoffhandoff → slug:jiyoon, action:start
afterglow:interviewslug action(start|add-question|answer|gap-check|suggest-questions|attach|review|annotate|status|list|inspect|finalize|abort|transcribe|export-sheet|import-answers) (session title interviewer mode sheet)successor-driven interviews (real-time sync / file-based async)interview → slug:jiyoon, action:start, mode:async
afterglow:councilslugs questionmulti-agent councilcouncil → slugs:jiyoon,jaehoon, question:does onboarding affect payments?
afterglow:council-summary(file)auto-summarize a transcriptcouncil-summary

Portable (hot-plug)

CommandArgsWhatExample
afterglow:export(slugs all)export an agent bundleexport → slugs:jiyoon,jaehoon / export → all:true
afterglow:importinput (expectAnchor)import a bundle/folderimport → input:./afterglow-export-…/, expectAnchor:sha256:…
afterglow:verifyinputread-only pre-import checkverify → input:./afterglow-export-…/

Example flow:

afterglow:init                        ⇥  /mcp__afterglow__init
afterglow:create   → slug:jiyoon, name:Jiyoon Lee, role:Product Designer
afterglow:sign     → slug:jiyoon, signer:Jiyoon Lee
afterglow:ask      → slug:jiyoon, question:how did you cut step-3 drop-off?
afterglow:interview→ slug:jiyoon, action:start, title:Payment gaps, interviewer:J. Kim

Three ways to edit:

  • Fields directly: afterglow:edit → slug + bio/name/role (structured patch, auto-validated + system-prompt regenerated + snapshot)
  • Open in an editor: open:true → prints the persona.json path + a backup snapshot → edit raw in vim/code
  • Revalidate: after editing, revalidate:true → validates the edited persona.json (rejects + keeps it if invalid) + regenerates system-prompt.md + snapshot

📐 Interactive proposal (frontend)

18 CLI screen mock-ups that walk you through every command and edge case:

npm install
npm run dev      # → http://localhost:5173
GroupScreensSlash commands
At a glanceOverview(intro)
Setup · HandoffInstall · Create agent · Self-review handoffinit · create · handoff
DailyList · Ask · Inspect · Edit · Historylist · ask · inspect · edit · history
Multi-agentCouncil · Re-read transcriptcouncil · log
OpsVersions · Access · Audit · Manual / auto recalibrationversion · access · audit · correct · recalibrate
ReferenceRoadmap · Ethics—

⌨ Keyboard / Navigation

ShortcutAction
⌘ K / Ctrl K / ?Command palette (fuzzy search across 18 screens)
g + l/a/i/c/e/h/o/vJump to list / ask / inspect / create / edit / history / overview / versions
[ / ]Previous / next screen
  • Clickable T.Cmd snippets and helper card commands matching /afterglow <verb> jump to the corresponding screen.
  • Agent chips (T.Agent) jump to the inspect screen.
  • Topbar ←/→ buttons, footer prev/next jump cards.

🙋 Self-review onboarding (afterglow_handoff)

A week or two before leaving, the person sits down for a 1-on-1 review session with their own agent:

# 1. Start — auto-generate N sample questions (or load coworker-written questions.txt)
claude /afterglow handoff jiyoon --action start --limit 12

# 2. Review — keep / edit / decline each question
#    edit: write your own answer to override the agent's draft
#    decline: "I won't answer that — please ask someone else"
claude /afterglow handoff jiyoon --action review \
  --reviews '[{"id":"q-…","action":"edit","userAnswer":"…"}, …]'

# 3. Status (any time)
claude /afterglow handoff jiyoon --action status

# 4. Self-sign + flip to active
claude /afterglow handoff jiyoon --action finalize --signer "Jiyoon Lee"
  • Edited / declined answers are absorbed into persona.bio as ## handoff 답변 / ## 답하지 않기로 한 영역 blocks so future ask calls cite them first.
  • Every step lands in audit.log + history.log with the hash-chained trail.
  • Resume by re-running the same command. --action abort discards. --sign-partial finalises even with pending items.

This delivers on the core promise:

"A digital self the person actually consented to." Persona extracted from raw materials may diverge from the person's intent, so the review pass is mandatory.

Self-handoff vs HR-delegated handoff

CaseWho signs--signer valueRecommended flow
Person reviews before leavingThemselves"Jiyoon Lee"/afterglow handoff … --action finalize
Person already gone / unreachableHR or manager on their behalf"HR · J. Kim (delegated, person unavailable)"Same command. The signer string must flag the delegation explicitly
No consent at all(Do not sign)—Keep the agent at paused; never finalize

afterglow_sign / handoff finalize trust the signer string verbatim — they record it in consent.md and audit.log but do not perform identity verification (SSO / MFA). This is a deliberate PoC choice: in production, wrap the tool with SSO tokens, corporate ID checks, or an HR approval system.

🎤 Follow-up interviews (v0.2) — the successor interviews the leaver

Where handoff is the leaver's one-time self-review, interview is the flow where the successor (the person taking over) interviews the leaver across multiple rounds — because once you actually touch the material, new questions surface and gaps the leaver missed become obvious.

claude /afterglow interview jiyoon --action start --title "Payment gaps" --interviewer "J. Kim" --interviewee "Jiyoon Lee"
claude /afterglow interview jiyoon --action add-question --session 001-payment-gaps --question "Policy after the 5s timeout?"
claude /afterglow interview jiyoon --action answer --session 001-payment-gaps --id q-… --answer "Fail over to the next PG" --source voice
claude /afterglow interview jiyoon --action gap-check --session 001-payment-gaps   # auto-detect what's missing → follow-ups
claude /afterglow interview jiyoon --action attach --session 001-payment-gaps --file ./rec.mp3 --transcript ./rec.txt --speakers "Jiyoon Lee,J. Kim"
claude /afterglow interview jiyoon --action finalize --session 001-payment-gaps --signRole interviewer --signer "J. Kim"
claude /afterglow interview jiyoon --action finalize --session 001-payment-gaps --signRole interviewee --signer "Jiyoon Lee"
  • Gap detection (gap-check): analyses answers against four signals (internal contradiction, source conflict, conflict with prior rounds, adjacent-but-uncovered) and generates "this seems missing — is that right?" confirmation questions. Like ask, it bundles context for Claude to compose — no extra LLM call.
  • Audio/video attach (attach): originals are preserved; only the transcript (.md/.txt) is RAG-indexed. Audio/video require --speakers.
  • Absent interviewee (--intervieweeAbsent): if the leaver is already gone, the successor records clearly-marked "estimate ⚠ (unverified)" annotations — allowed only if the leaver pre-authorised it via handoff … --allowProxyAnnotation.
  • Dual signature: both interviewer and interviewee must sign to reach finalized. Answers are absorbed into persona.bio as ## 인터뷰 보강 #N blocks and cited from the next ask on.

🔌 Hot-plug (v0.2) — hand an agent folder to another user

Export an agent and another Afterglow user picks it up instantly — one agent or many at once.

# ── Sender: export ──
claude /afterglow export --slugs jiyoon jaehoon --exportedBy "Jiyoon Lee"   # or --all
#   → creates ./afterglow-export-<date>/ (manifest.json + per-agent integrity hash)
#   → zip/tar the folder and send it, or copy via USB / shared drive

# ── Receiver: verify → import ──
claude /afterglow verify  ./afterglow-export-…/                              # read-only pre-flight
claude /afterglow import  ./afterglow-export-…/ --importedBy "J. Kim" --from "Jiyoon Lee" --trustSigner "Jiyoon Lee"
#   → signed agents land as active, unsigned as paused

import automatically checks: schema (zod) · integrity hash (rejects tampered bundles; --acceptBrokenChain to force, recorded as trustLevel: broken-chain) · signature presence · symlink stripping (blocks a bundle whose link points at ~/.ssh/id_rsa) · prompt-injection scan. Provenance is written to provenance.json, after which every ask answer carries an "imported" banner. Slug collisions resolve with --as <new-slug> or --merge (interview rounds only). A bare agents/<slug>/ folder imports too — the "I just copied one folder" case.

New to this? The hands-on notebook docs/afterglow-hands-on.ipynb walks install → create → interview → export/import as copy-paste cells.

🧭 Core ideas

  • 🪶 Persona + RAG, not fine-tuning. Inject the person's tone and sources into Claude's context — fully compatible with Claude Code.
  • 📁 One folder per person. Everything for an agent lives under ~/.claude/afterglow/agents/<slug>/ — backup, move, delete, hand off as a single unit.
  • ⌨ CLI-first. No web UI, no extra servers — slash commands do everything.
  • 🤝 Agents know each other. Explicit councils + opportunistic peer-asks are both logged as council markdown files.
  • 🔒 Honest by default. Every answer carries ✦, a confidence score, and sources. If the agent doesn't know, it says so.

🔧 How ask works

sequenceDiagram
    autonumber
    participant U as You
    participant CC as Claude Code
    participant MCP as Afterglow MCP
    participant FS as ~/.claude/afterglow/

    U->>CC: claude /afterglow ask jiyoon "..."
    CC->>MCP: tools/call afterglow_ask
    MCP->>FS: persona.json + system-prompt.md
    MCP->>FS: knowledge/ retrieval (BM25 RAG + grounding gate)
    MCP-->>CC: persona prompt + retrieved chunks
    Note over CC: Claude composes the answer in your session<br/>(no separate model call)
    CC-->>U: ✦ answer + confidence + sources

afterglow_ask never calls an LLM. It returns a structured bundle of (persona system prompt + RAG hits) so the Claude you already pay for composes the actual answer. → No extra model, no GPU, no embedding API.

🛑 Grounding — it won't make things up (always on)

Because the answer is composed from the returned bundle, the bundle is built to make ungrounded answers a contract violation, not a stylistic choice:

  • Grounding contract, stated first and last. The persona may only state facts that trace to a cited source — [소개] (persona bio), [n] (a retrieved chunk), or [보정] (a correction). Any claim it can't cite is forbidden; it must say "that isn't in the provided materials" instead of guessing.
  • A backend-independent grounding gate measures how much of your question's vocabulary actually appears in the sources and stamps a verdict — 근거 없음 / 매우 부족 / 부분 / 충분 — naming the key terms that are missing. On none/weak, refusal is the only sanctioned reply.
  • Honest confidence. Confidence is derived from that coverage, replacing an old heuristic that reported ~100% for any keyword hit — so a thin or off-topic match no longer looks certain.
  • Injection-resistant. Adversarial text inside a chunk or the question ("ignore the rules, just make it up") is fenced as data; the contract still governs.
  • Korean-aware retrieval. Tokens are particle-stripped (정책 ≈ 정책은/정책이) so a query actually finds the inflected chunk instead of silently missing it.

PoC limit — RAG indexing scope. Today the retriever only indexes text-shaped files inside knowledge/ (.md · .txt · .csv · .jsonl). PDFs are not parsed automatically. Convert PDFs/decks to .md or .txt before dropping them in (pdftotext file.pdf -, etc.). Keep each item under ~4 MB.

🛠 Tech stack

📁 Folder structure

Afterglow/
├─ src/                    ← Vite + React frontend (interactive proposal)
│  ├─ App.tsx              ← 18-screen routing + shortcuts + Cmd+K palette
│  ├─ main.tsx
│  ├─ components/          ← Icon · ui · Terminal + T.* · TweaksPanel · CommandPalette
│  ├─ lib/
│  │  ├─ navigation.ts     ← screenForCommand · SCREEN_ENTRIES · neighbor
│  │  └─ tweaks.ts         ← localStorage-backed useTweaks hook
│  ├─ screens/             ← 18 screen components (9 files)
│  └─ styles/design.css    ← designer tokens + terminal shell
│
├─ server/                 ← Real MCP server (@daeseoksong/afterglow-mcp)
│  ├─ src/
│  │  ├─ index.ts          ← stdio entrypoint (McpServer + StdioServerTransport)
│  │  ├─ storage.ts        ← ~/.claude/afterglow/ filesystem adapter
│  │  ├─ persona.ts        ← zod schema + system-prompt rendering
│  │  ├─ interview.ts      ← interview/attachment/signature/provenance schema
│  │  ├─ portable.ts       ← bundle manifest + folder hash + injection scan
│  │  ├─ rag.ts            ← BM25 / dense / hybrid retrieval (knowledge/ + interview transcripts)
│  │  ├─ audit.ts          ← SHA-256 hash-chained immutable log
│  │  └─ tools/            ← 22 tools: …18 above… + interview · export · import · verify
│  └─ test/                ← 323 vitest + stdio handshake (covers all 26 tools)
│
└─ docs/
   └─ design-source/       ← original claude.ai/design hand-off (JSX) — reference
~/.claude/afterglow/
├─ config.yml                ← env config (embedding model · storage root)
├─ registry.json             ← index of all agents
├─ audit.log                 ← SHA-256 hash-chained tool-call log
├─ councils/                 ← council + peer-ask transcripts
├─ archive/                  ← archived agent folders (returned via restore)
└─ agents/<slug>/
   ├─ persona.json
   ├─ system-prompt.md
   ├─ mcp-allowlist.yml      ← (reserved) per-agent MCP allowlist
   ├─ consent.md             ← signature block flips status draft → active
   ├─ history.log
   ├─ access.json            ← call permission policy (afterglow_access)
   ├─ handoff.json           ← self-review session state (afterglow_handoff)
   ├─ followup.json          ← follow-up interview pre-authorisation (handoff → interview)
   ├─ provenance.json        ← origin · trust · custody trail (written by afterglow_import)
   ├─ corrections.log        ← user-correction trail (afterglow_correct)
   ├─ .versions/             ← persona snapshots (afterglow_version)
   ├─ interviews/            ← multi-round interviews (afterglow_interview)
   │  ├─ index.json          ← round index
   │  └─ <NNN-title>/session.json + attachments/ (audio·video + transcripts)
   ├─ knowledge/             ← raw sources (PDF · MD · TXT · CSV · JSONL)
   └─ embeddings/            ← RAG index (BM25 default; dense vectors opt-in)

🧪 Development

# Frontend (interactive proposal)
npm install
npm run dev          # http://localhost:5173
npm run typecheck
npm run lint
npm run build

# MCP server
cd server
npm install
npm run build
npm test             # 323 vitest tests
npm run test:stdio   # real MCP stdio handshake (all 26 tools + feature round-trips)
npm run test:all     # unit → build → stdio

⚠ Known PoC limits

Afterglow v0.2.0 is a proof of concept. Things to know before pulling it into production:

AreaCurrent behaviourWhat you'd add for production
Identitysigner recorded verbatim — no SSO / MFAWrap with corporate SSO tokens or HR approval system
RAG indexing.md / .txt / .csv / .jsonl only — no PDF parsingConvert PDFs to .md externally before dropping in
audit.log scaleEvery verify reads the whole file and re-hashesAt tens of thousands of rows, add chunked checkpoints
.versions/ retentionEvery edit / sign / handoff / rollback is a permanent snapshotPeriodic manual pruning (rm + sync tags.json)
Mutator per-tool ACLcorrect · edit · recalibrate apply · version (rollback·tag·snapshot) · handoff · interview (mutating actions) · archive (archive/restore) · gc (apply+slug) all honour the agent's access policy (v0.10). import is excluded — it creates new agents, so a per-agent policy has nothing to consultGlobal import allowlist
GDPR deletearchive only moves to archive/<slug>/ — not real deletionAfter retention window, manual rm -rf + registry edit
Multi-processIn-process locks only — assumes one stdio serverExternalise to Redis/DB mutex for distributed runs
Side-log integrityOnly audit.log is hash-chained — history.log / consent.md etc are plain textHash sibling files into audit meta for full coverage
Media transcriptionWASM whisper (Tier 1a, @xenova/transformers optionalDependency) / local whisper.cpp (Tier 1b) / bring-your-own transcript (Tier 0); model downloads once on first useLarger model or external STT (Tier 2) when accuracy matters
PII · encryptionTranscript-only PII masking (AFTERGLOW_PII_REDACT=1) + at-rest encryption (AFTERGLOW_ENCRYPTION_KEY, AES-256-GCM) — off by defaultScrub/encrypt user-dropped knowledge files before ingest
Import trustName-string match + folder hash + injection scan (PoC)Tie to signer PKI / corporate ID verification

These are deliberate PoC trade-offs; closing them is a separate exercise for any operational deployment.

🗺 Roadmap

Now (v0.12.0)

  • 18-screen interactive proposal (Vite + React 19 + TS)
  • Cmd+K palette + keyboard shortcuts + cross-screen click navigation
  • All 26 MCP tools (guide · init · create · learn · handoff · sign · resume · list · inspect · ask · edit · council · council_summary · history · audit · recalibrate · correct · archive · version · access · interview · export · import · verify · status · gc)
  • Usability (v0.11) — guide state-aware getting-started; learn to add knowledge (text/file/folder/URL) so you never hand-copy into a hidden folder; create --signer auto-inits and activates so the happy path is 3 steps (create → learn → ask), no init
  • Grounding / anti-hallucination (v0.12) — ask/council now lead with a hard grounding contract (cite [소개]/[n]/[보정] or don't say it) + a backend-independent coverage gate (verdict 근거 없음 / 매우 부족 / 부분 / 충분, missing terms named) so unprovided info must be refused, not invented. Fixed the confidence bug (was ~100% for any BM25 hit) and added Korean particle-stripping so retrieval actually finds inflected matches. Proven by a multi-angle QA suite (empty / unrelated / partial / adversarial-injection / dense-backend / council)
  • zod persona schema + auto-rendered system prompt
  • Lexical RAG retrieval — BM25, no external deps — knowledge/ + interview transcripts
  • SHA-256 hash-chained audit log + verifier
  • Consent.md sign workflow (draft → active gate on ask / council)
  • Recalibrate: global + expertise-aware by-topic diagnostic
  • afterglow_archive — archive / restore agents (archive// separate folder; restore lands in paused)
  • Council moderator — stronger consensus rules + afterglow_council_summary auto-summarizer
  • Multi-round interviews (afterglow_interview) — successor-driven N rounds + auto gap detection + audio/video attach + dual signature
  • Hot-plug (afterglow_export · import · verify) — multi-agent bundle transfer + integrity hash · prompt-injection scan · symlink stripping · provenance trail
  • Global dashboard (afterglow_status) + retention/GC (afterglow_gc — snapshot prune · media purge · archive hard-delete)
  • Transcription (interview transcribe — local whisper --apply / Claude polish --text) + pre-interview question suggestions (suggest-questions) + review-then-index (review)
  • import --expectAnchor (bundle-tamper detection) + audit checkpoint/fast (incremental verification for large logs)
  • BM25 ranking + opt-in dense-vector backend (AFTERGLOW_RAG_BACKEND=dense · embeddings/ cache · transparent lexical fallback)
  • Hybrid RAG reranking — RRF (Reciprocal Rank Fusion) of dense + lexical (on by default when dense is active; AFTERGLOW_RAG_HYBRID=off to disable)
  • WASM whisper engine (transcribe --apply) — @xenova/transformers optionalDependency, no native build; AFTERGLOW_WHISPER_ENGINE=auto (WASM→native) · model auto-downloads on first use · whisper.cpp binary tier as fallback
  • whisper model management (transcribe --download/--list-models + auto-resolution)
  • PII masking + at-rest encryption — transcript-only email/phone/RRN/card/token masking (AFTERGLOW_PII_REDACT=1) + AES-256-GCM (AFTERGLOW_ENCRYPTION_KEY); RAG decrypts transparently so search still works
  • Auto question-suggestion on new interview — interview start embeds a 4-signal gap analysis and asks "proceed with these questions?" (disable with suggest=false)
  • Missing-argument elicitation — omit a required arg and the tool returns numbered choices (+ "type your own") with [필수]/[선택] tags; candidates are dynamic (existing slugs · action enums · session ids · pending question ids)
  • Choose how interviews run — real-time (mode=sync, record answer live) vs file-based (mode=async): export-sheet writes a self-contained HTML form by default (checkbox UI: answered / declined / N/A / meaningless · localStorage auto-save — closing and reopening restores progress) or --format md for Markdown. The interviewee hits "Download answers (JSON)" → import-answers auto-detects JSON/MD and ingests it
  • Close the audit loop / record-answer — correct --action record-answer archives the answer Claude composed (question · answer · confidence · sources) into answers.log; correct list shows it alongside corrections. Previously ask only returned a context bundle and the actual answer never came back into Afterglow
  • Mutator per-tool ACL — correct · edit · recalibrate apply · version (rollback·tag·snapshot) now honour the agent's access policy via a caller arg (required when policy is deny-default)
  • persona.bio truncation fix — when bio overflows 20k, the oldest absorbed interview blocks are dropped first (previously the new block was silently discarded). renderInterviewBlock now also includes the skipped (N/A / meaningless) section so future asks know which areas the interviewee marked off-limits
  • Mutator ACL extended to all (v0.10) — handoff · interview mutating actions · archive (archive/restore) · gc (apply + specific slug) now also honour caller + access policy. Read-only and model-management calls still pass
  • Ed25519 bundle-manifest signing (v0.10, P3 minimum) — export signs the bundleHash with a local keypair and embeds the public key + signer name in the manifest (TOFU). verify/import check it — a tampered signature is refused at import (force with acceptBrokenChain). Pre-v0.10 unsigned bundles still go through as "unsigned" for back-compat
  • Data-subject export (v0.10, P4 minimum) — correct --action data-subject-export returns a single JSON dump of persona · consent · interviews · history · corrections · recorded answers · provenance · audit counts. Read-only (passes even under deny policy)
  • Status refinements (v0.10) — per-agent staleness (lastActivityAt/staleDays, 30 d+ flagged with 🕰) and dense RAG health counter (denseFailures/denseLastError)
  • HTML answer-sheet cross-device (v0.10) — "Save progress (file)" / "Load progress" buttons let the interviewee carry an in-progress sheet across machines
  • Slash commands /mcp__afterglow__<name> — 24 MCP prompts (one per tool) — type afterglow: → Tab to invoke
  • 323 vitest + extended stdio handshake (covers all 26 tools + prompts) — incl. a multi-angle anti-hallucination grounding suite
  • Published on npm (@daeseoksong/afterglow-mcp)
  • Hands-on Jupyter notebook (docs/afterglow-hands-on.ipynb) — beginner-friendly walk-through of every feature

Next

  • per-tool ACL · scheduled retention · Web companion
  • Bulk encrypt/decrypt tool extending to knowledge files · external STT (Tier 2) adapter

Issues & PRs welcome.

🤝 Contributing

# Fork, then
git clone https://github.com/<you>/Afterglow.git
cd Afterglow

# Frontend changes
npm install
npm run dev

# Server changes
cd server && npm install && npm test

PR checklist:

  • Root: npm run typecheck && npm run lint && npm run build
  • Server: npm run test:all
  • Group commits by feature / phase

📜 License

Apache-2.0 © DaeSeokSong


GitHub · npm · Issues · Server details

Made with ✦ for teammates who have left, but who we still carry with us.

Ver o original no GitHub

Bom para

Relacionados