fleet-memory/hindsight-docs/docs/sdks/integrations
Ben 0b17a67c70
feat: add Hindsight memory integration for OpenAI Codex CLI (#730)
* feat(codex): add Hindsight memory integration for OpenAI Codex CLI

Hooks-based integration that gives Codex CLI long-term memory via Hindsight.
Three hooks keep memory in sync: SessionStart (daemon pre-warm), UserPromptSubmit
(recall + context injection), Stop (retain conversation to memory).

Key differences from the Claude Code integration:
- Codex transcript format: JSONL with {msg: {type, message}} (user_message/agent_message)
- No CODEX_PLUGIN_ROOT env var — install.sh writes hooks.json with absolute paths
- State stored in ~/.hindsight/codex/state/ (not CLAUDE_PLUGIN_DATA)
- No async: true in hooks (not supported by Codex)
- No SessionEnd event
- hooks.json written to ~/.codex/hooks.json with codex_hooks = true in config.toml

* fix(codex): fix transcript parser for actual Codex disk format

Codex stores sessions as rollout-*.jsonl with response_item entries:
  User:      {type:response_item, payload:{type:message, role:user, content:[{type:input_text, text:...}]}}
  Assistant: {type:response_item, payload:{type:message, role:assistant, phase:final_answer, content:[{type:output_text, text:...}]}}

Previous parser expected an undocumented {msg:{type:user_message}} format from the Rust protocol spec
that does not match the actual on-disk storage format.

* feat(codex): add reflect mode to UserPromptSubmit hook

Add recallMode config option (default: 'recall') that switches the
UserPromptSubmit hook between:
- 'recall': existing behavior, fast raw facts list
- 'reflect': agentic synthesis loop, returns coherent prose answer

Also adds reflect() method to HindsightClient and HINDSIGHT_RECALL_MODE
env var override. Reflect uses a 25s timeout (vs 10s for recall).

* feat(codex): auto mode for recall/reflect selection

Add recallMode: 'auto' (new default) that picks the operation per-query:
- Synthesis patterns (what do you know, what's my, summarize, etc.) → reflect
- All other prompts → recall (fast, raw facts, better for code tasks)

* feat(codex): add automated test suite and finalize recall-only mode

* docs(codex): add docs page and sidebar entry for Codex CLI integration
2026-03-30 10:51:53 +02:00
..
ag2.md docs: add AG2 integration page (#723) 2026-03-27 10:58:42 +01:00
agno.md docs: add 0.4.19 release blog post, Agno and Hermes integration pages (#608) 2026-03-18 17:35:54 +01:00
ai-sdk.mdx doc: add langgraph and nemoclaw (#633) 2026-03-20 16:18:05 +01:00
chat.md doc: add langgraph and nemoclaw (#633) 2026-03-20 16:18:05 +01:00
claude-code.md docs(claude-code): tidy configuration reference and sync README (#706) 2026-03-26 14:07:35 +01:00
codex.md feat: add Hindsight memory integration for OpenAI Codex CLI (#730) 2026-03-30 10:51:53 +02:00
crewai.md doc: add langgraph and nemoclaw (#633) 2026-03-20 16:18:05 +01:00
hermes.md feat(hermes): file-based config + updated docs (#686) 2026-03-25 16:11:38 +01:00
langgraph.md doc: add langgraph and nemoclaw (#633) 2026-03-20 16:18:05 +01:00
litellm.md doc: add langgraph and nemoclaw (#633) 2026-03-20 16:18:05 +01:00
llamaindex.md feat: add LlamaIndex integration (#672) 2026-03-30 10:43:35 +02:00
local-mcp.md feat: expand MCP tool surface area with 18 new tools and enhanced parameters (#435) 2026-02-25 10:26:46 +01:00
nemoclaw.md doc: add langgraph and nemoclaw (#633) 2026-03-20 16:18:05 +01:00
openclaw.md feat(openclaw): add recallInjectionPosition config to preserve prompt cache (#710) 2026-03-26 16:09:25 +01:00
pydantic-ai.md doc: add langgraph and nemoclaw (#633) 2026-03-20 16:18:05 +01:00
skills.md Replace waitlist links with direct Hindsight Cloud signup URL (#349) 2026-02-11 20:51:32 +01:00
strands.md feat: add Strands Agents SDK integration with Hindsight memory tools (#659) 2026-03-24 17:21:30 +01:00